# How to integrate Daytona MCP with OpenClaw

```json
{
  "title": "How to integrate Daytona MCP with OpenClaw",
  "toolkit": "Daytona",
  "toolkit_slug": "daytona",
  "framework": "OpenClaw",
  "framework_slug": "openclaw",
  "url": "https://composio.dev/toolkits/daytona/framework/openclaw",
  "markdown_url": "https://composio.dev/toolkits/daytona/framework/openclaw.md",
  "updated_at": "2026-06-18T09:23:41.739Z"
}
```

## Introduction

OpenClaw is the fastest growing agent harness out there, which can work 24/7 to automate almost any kind of tasks. However, its capabilities are limited to the tools it has access to. Composio allows your OpenClaw to access Daytona with authentication management handled for you. You can execute actions on Daytona via your favorite OpenClaw interface (Telegram, WhatsApp, TUI, etc), whichever you prefer.

## Also integrate Daytona with

- [OpenAI Agents SDK](https://composio.dev/toolkits/daytona/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/daytona/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/daytona/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/daytona/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/daytona/framework/codex)
- [Hermes](https://composio.dev/toolkits/daytona/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/daytona/framework/cli)
- [Google ADK](https://composio.dev/toolkits/daytona/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/daytona/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/daytona/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/daytona/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/daytona/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/daytona/framework/crew-ai)

## TL;DR

### Why use Composio?
Apart from a managed and hosted MCP server, you will get:
- Programmatic tool calling allows LLMs to write its code in a remote workbench to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling.
- Handling Large tool responses out of LLM context to minimize context rot.
- Dynamic just-in-time access to 20,000 tools across 1000+ other Apps for cross-app workflows. It loads the tools you need, so LLMs aren't overwhelmed by tools you don't need.

## Connect Daytona to OpenClaw

### How to install Daytona with OpenClaw
### Using Composio API Key and Setup Prompt
- Go to [dashboard.composio.dev](https://dashboard.composio.dev/login?next=/~/org/connect/clients/openclaw&utm_source=toolkits&utm_medium=framework_template&utm_campaign=openclaw&utm_content=setup_prompt)
- Copy the setup prompt
- Run it in your OpenClaw chat interface.
- Authenticate Daytona from the [dashboard](https://dashboard.composio.dev/login?next=/~/org/connect/clients/openclaw&utm_source=toolkits&utm_medium=framework_template&utm_campaign=openclaw&utm_content=authenticate)
- Go back to your OpenClaw interface and start asking questions.
### Using OpenClaw/Composio Plugin
1. Install OpenClaw Composio plugin

```bash
openclaw plugins install @composio/openclaw-plugin
```

## What is the Daytona MCP server, and what's possible with it?

The Daytona MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Daytona account. It provides structured and secure access so your agent can perform Daytona operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DAYTONA_ARCHIVE_SANDBOX` | Archive Sandbox | Archives a sandbox in the Daytona platform. Use this action when you need to archive a sandbox that is no longer needed but should be preserved for future reference. The sandbox will be marked as archived and its state will change to reflect the archival status. Note: Archiving a sandbox does not delete it immediately. The sandbox can potentially be restored or recovered from an archived state depending on the platform configuration. |
| `DAYTONA_CANCEL_ORGANIZATION_INVITATION` | Cancel Organization Invitation | Cancels a pending organization invitation. Use when you need to revoke an invitation that has been sent but not yet accepted by the recipient. This action is irreversible — once an invitation is cancelled, it cannot be reactivated and the recipient will no longer be able to accept it. The cancelled invitation would need to be re-sent as a new invitation if access is still desired. |
| `DAYTONA_CHECKOUT_GIT` | Checkout Git Branch | [DEPRECATED] Checkout a branch or commit in a git repository within a sandbox. Use this action when you need to switch branches or checkout a specific commit in a git repository that exists within a sandbox toolbox. This operation modifies the working tree of the repository. Note: This endpoint is deprecated. Consider using alternative approaches for git operations if available. The sandbox must be in a running state for this operation to succeed. |
| `DAYTONA_CLONE_REPOSITORY` | Clone Repository | Clones a Git repository into a sandbox toolbox. Use this action when you need to clone a public or private Git repository into a specific directory within a sandbox. Supports optional branch selection and commit checkout. This is commonly used to set up a development environment or fetch source code for further operations. Note: Credentials (username/password) should only be provided when the target repository requires authentication. The sandbox must be running to perform this operation. |
| `DAYTONA_CREATE_API_KEY` | Create API Key | Creates a new API key for the organization. Use when you need to generate a new API key that can be used to authenticate API requests. The created API key value is only returned once in the response and cannot be retrieved again, so it must be stored securely. This action requires appropriate organization permissions. |
| `DAYTONA_CREATE_BACKUP` | Create Sandbox Backup | Initiates a backup operation for an existing sandbox environment. Use this action when you need to create a point-in-time snapshot of a sandbox that can be used for restoration or cloning purposes. The backup operation is asynchronous and the status can be tracked via the backupState field in the response (Pending -> InProgress -> Completed or Error). Note: This action creates a backup resource. Ensure the sandbox is in a suitable state for backing up. Large sandboxes may take longer to complete the backup. |
| `DAYTONA_CREATE_FOLDER_FILES` | Create Folder in Sandbox | Creates a new folder inside a sandbox's filesystem. Use this action when you need to create a directory within a running sandbox's filesystem. This is useful for organizing files, preparing directory structures, or setting up paths for subsequent file operations. Note: This endpoint is deprecated. Consider using alternative methods for folder creation if available. |
| `DAYTONA_CREATE_ORGANIZATION` | Create Organization | Creates a new organization in Daytona. Use this action when you need to set up a new organization with a specific name and default region configuration. This action creates a top-level organization entity that can manage sandboxes, users, and resources within the specified region. |
| `DAYTONA_CREATE_ORGANIZATION_INVITATION` | Create Organization Invitation | Creates an invitation to join an organization with specified roles and permissions. The invitation will be sent to the provided email address. Use this action when you need to invite a new member to an organization with specific role assignments. The invitation email will include a link to accept the invitation. |
| `DAYTONA_CREATE_ORGANIZATION_ROLE` | Create Organization Role | Creates a new organization role with specified permissions. Use this action when you need to define custom roles for organization members, allowing fine-grained control over what resources they can access and what operations they can perform. Common use cases include creating roles like "Developer" (with sandbox write access), "Viewer" (read-only access), or "Admin" (full access to all resources). |
| `DAYTONA_CREATE_PROCESS_SESSION` | Create Process Session | Creates a new session in the sandbox for process management. Use this action when you need to establish a new process session within a running sandbox environment. This enables managing process execution and state within the Daytona platform. The session can be used to track and manage process-related operations. Note: This endpoint is deprecated. Consider using alternative methods for process session management if available. The sandbox must be in a running state for this operation to succeed. |
| `DAYTONA_CREATE_PTY_SESSION` | Create PTY Session | Creates a new PTY (pseudo-terminal) session in a sandbox. Use this action when you need to establish an interactive terminal session within a running sandbox environment. This enables real-time command execution and terminal interaction through the Daytona platform. The session can be configured with specific terminal dimensions (cols/rows), working directory, and environment variables. Note: This endpoint is deprecated. The sandbox must be in a running state for this operation to succeed. Consider alternative methods for terminal sessions if available. |
| `DAYTONA_CREATE_REGISTRY` | Create Docker Registry | Creates a new Docker registry for the organization. Use when you need to register a new container registry (such as Docker Hub, GCR, ECR, or other Docker registries) so that Daytona can pull images from it. The registry credentials are stored securely and used for pulling images when creating sandboxes. Ensure the provided credentials have appropriate permissions (typically read access to the registry). |
| `DAYTONA_CREATE_SANDBOX` | Create Sandbox | Creates a new sandbox environment for development or testing purposes. Use this action when you need to provision a new isolated environment with configurable compute resources (CPU, memory, GPU), networking options, and storage volumes. The sandbox can be customized with environment variables, labels, and automatic lifecycle management settings. Note: This action creates a new resource. Ensure you have the appropriate permissions in your organization before creating sandboxes. |
| `DAYTONA_CREATE_SNAPSHOT` | Create Snapshot | Creates a new snapshot resource that can be used as a base image for sandboxes. Use this action when you need to create a new snapshot with specific compute resources (CPU, memory, GPU, disk) and a container image. Snapshots define the base configuration that sandboxes will inherit when created from them. The snapshot can be built from a Dockerfile using the buildInfo parameter, or use an existing image via the imageName parameter. Note: Snapshots with tags like ":latest" are not allowed. Ensure the name parameter is unique within your organization. |
| `DAYTONA_CREATE_SSH_ACCESS` | Create SSH Access | Creates SSH access credentials for a sandbox environment. Use this action when you need to establish an SSH connection to a sandbox for administrative tasks, file transfers, or development operations. The returned credentials include a token and SSH command that can be used to connect to the sandbox securely. Note: SSH access tokens have a limited validity period. By default, they expire after 60 minutes. Use the expiresInMinutes parameter to customize the expiration time if needed. |
| `DAYTONA_CREATE_VOLUME` | Create Volume | Creates a new volume for storing data that can be attached to sandboxes. Use this action when you need to provision persistent storage for your sandbox environments. Volumes persist data across sandbox restarts and can be mounted to sandboxes to provide additional storage capacity. Note: This action creates a new storage resource. Ensure you have the appropriate permissions in your organization before creating volumes. |
| `DAYTONA_DEACTIVATE_SNAPSHOT` | Deactivate Snapshot | Deactivates a snapshot in the Daytona platform. Use this action when you need to deactivate a snapshot that is currently active. This will stop the snapshot from being used for new sandbox creations. Note: Deactivating a snapshot does not delete it. The snapshot data remains accessible but the snapshot is marked as inactive. |
| `DAYTONA_DELETE_API_KEY` | Delete API Key | Deletes an API key by its name. Use when you need to revoke access for an API key that is no longer needed or has been compromised. This action is irreversible — once an API key is deleted, it cannot be recovered and any systems using that key will immediately lose access. |
| `DAYTONA_DELETE_API_KEY_USER` | Delete API Key for User | Deletes an API key for a specific user. Use when you need to remove an existing API key associated with a user account, such as when cleaning up unused credentials or revoking access. This action is irreversible — once the API key is deleted, it cannot be recovered and any systems relying on that key will lose access. |
| `DAYTONA_DELETE_FILES` | Delete Sandbox File | Deletes a file inside a sandbox by its path. Use when you need to permanently remove a file from a sandbox that is no longer needed. This action is irreversible — once a file is deleted, it cannot be recovered. Ensure the file is not needed before proceeding with deletion. Note: This action uses a deprecated API endpoint. Consider migrating to an alternative method for file management when available. |
| `DAYTONA_DELETE_GIT_BRANCH` | Delete Git Branch | Deletes a branch from a git repository inside a sandbox by its name. Use when you need to permanently remove a git branch that is no longer needed. This action is irreversible — once a branch is deleted, it cannot be recovered unless it has been pushed to a remote. Ensure the branch has been properly merged or is no longer needed before proceeding. Note: This action uses a deprecated API endpoint. The API documentation marks this endpoint as [DEPRECATED]. Consider using alternative methods for git branch management when available. |
| `DAYTONA_DELETE_ORGANIZATION` | Delete Organization | Deletes an organization. Use when you need to permanently remove an organization from the system, including all associated data, members, and resources. This action is irreversible — once an organization is deleted, it cannot be recovered. All organization data, including workspaces, sandboxes, and member information, will be permanently lost. Ensure you have appropriate backups or have migrated necessary data before proceeding. |
| `DAYTONA_DELETE_ORGANIZATION_OTEL_CONFIG` | Delete Organization OTEL Config | Deletes the OpenTelemetry (OTEL) configuration for an organization. Use this action when you need to remove the OpenTelemetry settings that were previously configured for an organization's observability and tracing capabilities. This action is irreversible — once the OpenTelemetry configuration is deleted, the organization will no longer have OTEL tracing enabled and any previously collected telemetry data will no longer be accessible through the configured OTEL endpoint. A new configuration would need to be created to re-enable OpenTelemetry observability. |
| `DAYTONA_DELETE_ORGANIZATION_ROLE` | Delete Organization Role | Deletes an organization role. Use when you need to permanently remove a role from an organization, such as cleaning up unused custom roles or removing roles that are no longer needed. This action is irreversible — once a role is deleted, it cannot be recovered. Users who were assigned this role will lose the associated permissions and access. Ensure no active users or resources depend on this role before proceeding. |
| `DAYTONA_DELETE_PTY_SESSION` | Delete PTY Session | Deletes a PTY session and terminates the associated process. Use this action when you need to clean up an active PTY session that is no longer needed. This will terminate any process running in that session and release the associated resources. Note: This endpoint is deprecated. Consider using alternative methods for managing PTY sessions in new implementations. This action is irreversible — once the PTY session is deleted and the process is terminated, they cannot be recovered. |
| `DAYTONA_DELETE_RECORDING` | Delete Recording | Deletes a recording from the Daytona platform by its ID. Use when you need to permanently remove a recording that is no longer needed. This action is irreversible — once a recording is deleted, it cannot be recovered. Any data associated with the recording will be permanently lost. |
| `DAYTONA_DELETE_REGISTRY` | Delete Docker Registry | Deletes a Docker registry from the Daytona platform. Use when you need to remove an existing Docker registry configuration. This is an irreversible operation — once a registry is deleted, it cannot be recovered and any references to it in workspaces may fail until reconfigured. |
| `DAYTONA_DELETE_SANDBOX` | Delete Sandbox | Deletes a sandbox from the Daytona platform by its ID or name. Use when you need to permanently remove a sandbox that is no longer needed. This action is irreversible — once a sandbox is deleted, it cannot be recovered. Any data, processes, or configurations within the sandbox will be permanently lost. Ensure all important work has been saved or backed up before proceeding. |
| `DAYTONA_DELETE_SESSION` | Delete Session | Deletes a session from the Daytona platform by its ID. Use when you need to permanently remove a session that is no longer needed. This action is irreversible — once a session is deleted, it cannot be recovered. Any ongoing processes or data associated with the session will be permanently lost. |
| `DAYTONA_DELETE_SNAPSHOT` | Delete Snapshot | Deletes a snapshot from the Daytona platform by its ID. Use when you need to permanently remove a snapshot that is no longer needed. This action is irreversible — once a snapshot is deleted, it cannot be recovered. Any data stored in the snapshot will be permanently lost. |
| `DAYTONA_DELETE_VOLUME` | Delete Volume | Deletes a volume from the Daytona platform by its ID. Use when you need to permanently remove a volume that is no longer needed. This action is irreversible — once a volume is deleted, it cannot be recovered. Ensure all important data has been backed up before proceeding. Note: A volume cannot be deleted if it is in use by one or more sandboxes. |
| `DAYTONA_DOWNLOAD_FILE_DEPRECATED` | Download File (Deprecated) | [DEPRECATED] Downloads a file from a sandbox's toolbox filesystem. Use this action when you need to retrieve a file from the sandbox's toolbox. Note: This endpoint is deprecated. Consider using an alternative if available. This is a read-only operation that does not modify any resources. |
| `DAYTONA_DOWNLOAD_FILES` | Download Multiple Files | Downloads multiple files from a sandbox as a multipart/form-data bundle. Use this action when you need to retrieve multiple files from a sandbox in a single operation. The files are returned as a streamed multipart response where each file is a separate part. This is a read-only operation that does not modify any resources. |
| `DAYTONA_ENROLL_IN_SMS_MFA` | Enroll in SMS MFA | Enrolls the authenticated user in SMS-based multi-factor authentication. Use when you need to enable SMS-based MFA for the authenticated user account. This action initiates the enrollment process and returns a URL where the user can complete the MFA setup by providing their phone number. Note: After enrollment, the user must complete the verification process by visiting the returned URL and entering the verification code sent to their phone. |
| `DAYTONA_EXECUTE_COMMAND` | Execute Command | Executes a shell command within a running sandbox via the toolbox proxy. Use this action when you need to run shell commands, scripts, or any executable commands inside a sandbox environment. This is useful for automation tasks, running build commands, executing scripts, or performing system operations within the sandbox. The sandbox must be in a running state for this action to succeed. Command execution is synchronous and will wait for completion up to the specified timeout (default 10 seconds). |
| `DAYTONA_EXPIRE_SIGNED_PORT_PREVIEW_URL` | Expire Signed Port Preview URL | Expires a signed preview URL for a sandbox port. Use this action when you need to immediately invalidate a signed preview URL for a specific port on a sandbox, revoking access for anyone holding the token. This action is useful for security purposes when you need to quickly revoke access to a previously shared preview URL. This action is irreversible — once the signed preview URL is expired, the token will no longer provide access to the sandbox port, and a new signed preview URL must be generated if access is needed again. |
| `DAYTONA_FIND_IN_FILES_DEPRECATED` | Find In Files (Deprecated) | [DEPRECATED] Searches for text or patterns in files within a sandbox. Use this action when you need to find occurrences of a specific text or pattern across files in a sandbox. This is useful for code search, debugging, or locating specific content within the sandbox file system. This is a read-only operation. NOTE: This action is deprecated and may be removed in future versions. Consider using alternative search mechanisms if available. |
| `DAYTONA_FOCUS_ACCESSIBILITY_NODE` | Focus Accessibility Node | Focuses an accessibility node in a sandbox's computer use system. Use this action when you need to programmatically set focus to a specific accessibility node within a sandbox's desktop environment. This is particularly useful for UI automation workflows where you need to ensure a specific element has focus before performing keyboard or mouse actions on it. Note: The sandbox must have computer use enabled for this action to work. This action is idempotent — focusing the same node multiple times will have the same effect. |
| `DAYTONA_GET_API_KEY` | Get API Key | Retrieves an API key by its name. Use when you need to retrieve details about a specific API key, including its creation date, expiration, permissions, and usage statistics. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_AVAILABLE_ACCOUNT_PROVIDERS` | Get Available Account Providers | Retrieves all available account providers that can be used to authenticate and link accounts. Use when you need to discover which account providers (such as GitHub, GitLab, Google) are available for linking to the user's account. This is a read-only operation that does not modify any resources. Note: The list includes both the provider name (machine-readable) and displayName (human-readable) for each provider. |
| `DAYTONA_GET_BUILD_LOGS_URL` | Get Build Logs URL | Retrieves the build logs URL for a specific sandbox by its ID or name. Use this action when you need to access build logs for a sandbox, such as during troubleshooting build failures, monitoring build progress, or retrieving historical build information. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_COMMIT_HISTORY` | Get Commit History | Gets commit history from a repository in a sandbox toolbox. Use this action when you need to retrieve the commit history including: - Commit hash - Author name and email - Commit message - Timestamp This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_COMPUTER_USE_STATUS` | Get Computer Use Status | Retrieves the status of all VNC desktop processes in a sandbox. Use this action when you need to check the current state of all VNC desktop processes running within a sandbox. The status can indicate whether services are fully operational (active), partially running (partial), not running (inactive), or experiencing errors (error). This is useful for monitoring the health of computer use services and troubleshooting connectivity issues. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for checking computer use status in new implementations. |
| `DAYTONA_GET_CONFIG` | Get Daytona Config | Retrieves the Daytona platform configuration including URLs, OIDC settings, analytics, rate limits, and other platform-level settings. Use this action when you need to fetch the current Daytona configuration settings, such as the dashboard URL, proxy settings, SSH gateway configuration, analytics endpoints, or to check if maintenance mode is enabled. This is a read-only operation that returns the platform configuration. |
| `DAYTONA_GET_DISPLAY_INFO` | Get Display Info | Retrieves information about displays connected to a sandbox. Use this action when you need to get information about all displays connected to a sandbox, including their dimensions, positions, and active status. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for retrieving display information in new implementations. |
| `DAYTONA_GET_ENTRYPOINT_LOGS` | Get Entrypoint Logs | Retrieves entrypoint logs for a sandbox session. Use this action when you need to fetch the stdout, stderr, and combined output logs from an entrypoint process running within a sandbox. This is useful for debugging process initialization, monitoring entrypoint execution, or retrieving historical entrypoint log information. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_FILE_INFO` | Get File Info (Deprecated) | [DEPRECATED] Gets file info inside a sandbox toolbox. Use this action when you need to retrieve detailed information about a specific file or directory within a sandbox toolbox, including its size, permissions, ownership, and modification timestamps. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for file operations in newer integrations. |
| `DAYTONA_GET_GIT_HISTORY_DEPRECATED` | Get Git History (Deprecated) | [DEPRECATED] Get commit history from a git repository in a sandbox toolbox. Use this action when you need to retrieve the commit history of a git repository within a sandbox toolbox. This is a read-only operation that retrieves the commit log without modifying any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for git operations in newer integrations. |
| `DAYTONA_GET_HAS_SANDBOX_ACCESS` | Check Sandbox Access | Checks if the authenticated user has access to a specific sandbox. Use this action when you need to verify whether the current user has permission to access a particular sandbox before performing further operations on it. This is a read-only operation that does not modify any sandbox data. |
| `DAYTONA_GET_HEALTH` | Get Daytona Health Status | Retrieves the current health status of the Daytona service. Use when you need to verify that the Daytona API is running and accessible. This action is read-only and does not modify any data. This action is useful for monitoring, debugging connection issues, or confirming API availability before performing other operations. |
| `DAYTONA_GET_ORGANIZATION` | Get Organization | Retrieves detailed information about an organization by its unique identifier. Use when you need to fetch organization settings, rate limits, sandbox configurations, suspension status, OpenTelemetry settings, and other organization-level details. This is a read-only operation that returns the current organization state. |
| `DAYTONA_GET_ORGANIZATION_AUDIT_LOGS` | Get Organization Audit Logs | Retrieves audit logs for an organization. Use when you need to track user activities, monitor security events, investigate incidents, or meet compliance requirements. This action supports both page-based and cursor-based pagination. For fetching subsequent pages, use the nextToken from the previous response. Date range filtering can narrow results to specific time periods. |
| `DAYTONA_GET_ORGANIZATION_INVITATIONS_COUNT_USER` | Get Organization Invitations Count | Retrieves the count of organization invitations for the authenticated user. Use this action when you need to check how many organization invitations are pending for the currently authenticated user. This is a read-only operation that does not modify any data. The count includes all pending invitations across all organizations the user has been invited to. |
| `DAYTONA_GET_ORGANIZATION_USAGE_OVERVIEW` | Get Organization Usage Overview | Retrieves the current usage overview for an organization, including CPU, memory, disk, snapshot, and volume usage metrics across all regions. Use this action when you need to check an organization's current resource usage, such as monitoring quota consumption, planning capacity, or auditing resource utilization. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_PROCESS_STATUS` | Get Process Status | Retrieves the status of a specific VNC process in a sandbox. Use this action when you need to check if a particular VNC process (such as xfce4) is currently running within a sandbox. This is useful for monitoring process availability, verifying desktop environment readiness, or determining if a process needs to be started. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for checking process status in new implementations. |
| `DAYTONA_GET_PROJECT_DIR_DEPRECATED` | Get Project Dir (Deprecated) | [DEPRECATED] Gets the project directory path within a sandbox toolbox. Use this action when you need to retrieve the project directory path for a specific sandbox toolbox. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for determining the project directory in newer integrations. |
| `DAYTONA_GET_PTY_SESSION` | Get PTY Session | Retrieves information about a PTY (pseudo-terminal) session in a sandbox. Use this action when you need to fetch details about a specific PTY session within a sandbox, including its configuration (terminal dimensions, working directory, environment variables), creation timestamp, and active status. This is useful for monitoring PTY session state, checking if a session is still active, or retrieving session configuration details. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for managing PTY sessions in new implementations. |
| `DAYTONA_GET_PUSH_ACCESS` | Get Push Access | Retrieves temporary storage access credentials for pushing objects to object storage. Use this action when you need to upload or push objects to the Daytona object storage service. The returned credentials (access key, secret, session token, storage URL, and bucket name) are temporary and should be used immediately for the push operation. This is a read-only operation that does not modify any stored objects. Note: The returned credentials have a limited validity period. Use them promptly after retrieval for any object storage operations. |
| `DAYTONA_GET_REGISTRY` | Get Docker Registry | Retrieves details of a specific Docker registry by its unique identifier. Use this action when you need to fetch information about a particular Docker registry, including its URL, credentials, project association, and type. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_SANDBOX` | Get Sandbox | Retrieves details of a specific sandbox by its ID or name. Use this action when you need to fetch detailed information about a particular sandbox, including its configuration, state, resource quotas, labels, environment variables, volumes, and other metadata. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_SESSION_COMMAND_LOGS` | Get Session Command Logs | Retrieves logs for a specific command executed within a session. Use this action when you need to fetch the stdout, stderr, and combined output logs from a command that was executed in a sandbox session. This is useful for debugging command execution failures, reviewing command output, monitoring command performance, or retrieving historical command execution results. This is a read-only operation that does not modify any resources. Note: The follow parameter enables WebSocket-based real-time log streaming. |
| `DAYTONA_GET_SESSION_DEPRECATED` | Get Session (Deprecated) | [DEPRECATED] Retrieves details of a specific session in a sandbox toolbox. Use this action when you need to fetch information about a particular session, including its ID and the commands that have been executed within it. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for session management in newer integrations. |
| `DAYTONA_GET_SNAPSHOT` | Get Snapshot | Retrieves details of a specific snapshot by its ID or name. Use this action when you need to fetch detailed information about a particular snapshot, including its configuration, state, resource quotas, build information, and other metadata. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_SNAPSHOT_BUILD_LOGS` | Get Snapshot Build Logs | Retrieves build logs for a specific snapshot. Use this action when you need to access build logs for a snapshot, such as during troubleshooting build failures, monitoring build progress, or retrieving historical build information. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_TOOLBOX_PROXY_URL` | Get Toolbox Proxy URL | Retrieves the toolbox proxy URL for a sandbox by its ID or name. Use this action when you need to access the toolbox interface of a sandbox, enabling command execution and file management operations. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_TRANSIENT_PUSH_ACCESS` | Get Transient Push Access | Retrieves temporary registry access credentials for pushing snapshots. Use this action when you need to obtain short-lived authentication credentials to push Docker images or snapshots to the Daytona registry. The credentials expire after a short time, so use them immediately after obtaining them. This action is idempotent - calling it generates a fresh set of temporary credentials. |
| `DAYTONA_GET_USER` | Get Authenticated User | Retrieves the profile of the authenticated user. Use when you need to fetch details about the currently logged-in user, including their ID, email, name, creation date, and associated public keys. This action requires authentication and uses the bearer token provided in the request headers to identify the user. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_USER_HOME_DIR_DEPRECATED` | Get User Home Dir (Deprecated) | [DEPRECATED] Gets the user home directory path for a sandbox. Use this action when you need to retrieve the home directory path for a user within a sandbox toolbox. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for sandbox operations in newer integrations. |
| `DAYTONA_GET_VOLUME` | Get Volume | Retrieves details of a specific volume by its ID. Use this action when you need to fetch information about a particular volume, including its name, state, organization, creation timestamp, and last usage. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_WINDOWS` | Get Windows | Retrieves information about all windows in a sandbox. Use this action when you need to get a list of all windows currently open in a sandbox desktop environment. The response includes each window's position, dimensions, title, and active status. This is useful for monitoring the desktop state, automating window interactions, or determining which application is currently in focus. This is a read-only operation that does not modify any resources. |
| `DAYTONA_GET_WORK_DIR` | Get Working Directory | Gets the current working directory inside a sandbox toolbox. Use this action when you need to retrieve the current working directory path within a sandbox toolbox. This is a read-only operation that does not modify any resources. This is useful for determining the context for subsequent file operations or command execution within the sandbox. |
| `DAYTONA_GET_WORK_DIR_DEPRECATED` | Get Work Dir (Deprecated) | [DEPRECATED] Retrieves the working directory path of a sandbox toolbox. Use this action when you need to determine the current working directory path within a sandbox toolbox environment. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for determining sandbox working directories in newer integrations. |
| `DAYTONA_LIST_API_KEYS` | List API Keys | Lists all API keys for the organization. Use when you need to retrieve information about all available API keys, including their names, creation dates, expiration dates, and associated permissions. This is a read-only operation that does not modify any resources. Note: API key values are returned masked (e.g., "bb_********************def"). |
| `DAYTONA_LIST_AVAILABLE_REGIONS` | List Available Regions | Lists all available regions for the organization. Use this action when you need to retrieve information about all available regions, including their IDs, names, types, and associated URLs (proxy, SSH gateway, snapshot manager). This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_FILES_DEPRECATED` | List Files (Deprecated) | [DEPRECATED] Lists files and directories in a sandbox toolbox. Use this action when you need to retrieve the list of files and directories in a specific path within a sandbox toolbox. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for file listing in newer integrations. |
| `DAYTONA_LIST_GIT_BRANCHES` | List Git Branches (Deprecated) | [DEPRECATED] Lists all git branches from a repository in a sandbox toolbox. Use this action when you need to retrieve the list of git branches from a repository within a sandbox toolbox. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for git operations in newer integrations. |
| `DAYTONA_LIST_ORGANIZATION_INVITATIONS` | List Organization Invitations | Lists all pending organization invitations. Use this action when you need to retrieve all invitations for an organization, including pending, accepted, declined, or cancelled invitations. This is useful for managing organization membership and reviewing pending invitations. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_ORGANIZATION_INVITATIONS_USER` | List Organization Invitations for User | Lists all organization invitations for the authenticated user. Use when you need to retrieve pending and past organization invitations that have been sent to or received by the current user, including their status, assigned roles, and expiration details. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_ORGANIZATION_MEMBERS` | List organization members | Lists all members of a specific organization. Use when you need to retrieve information about all organization members, including their names, emails, roles, and assigned permissions. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_ORGANIZATION_ROLES` | List organization roles | Lists all roles available in an organization. Use when you need to retrieve information about all organization roles, including their names, descriptions, permissions, and whether they are global roles. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_ORGANIZATIONS` | List Organizations | Lists all organizations that the authenticated user has access to. Use this action when you need to retrieve a list of all organizations available to the authenticated user, including their settings, rate limits, and configuration. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_PROCESS_SESSION` | List Process Sessions | Lists all active process sessions in a sandbox. Use this action when you need to retrieve information about all active process sessions running within a sandbox. This includes session IDs and command history for each session. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for retrieving process session information in new implementations. |
| `DAYTONA_LIST_PTY_SESSIONS` | List PTY Sessions | Lists all active PTY sessions in a sandbox. Use this action when you need to retrieve information about all active pseudo-terminal (PTY) sessions running within a sandbox. This includes session identifiers, working directories, terminal dimensions, and environment variables. This is useful for monitoring active sessions, auditing terminal activity, or managing multiple concurrent terminal sessions. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. Consider using alternative methods for listing PTY sessions in new implementations. |
| `DAYTONA_LIST_REGISTRIES` | List registries | Lists all docker registries available in the organization. Use when you need to retrieve information about all configured docker registries, including their IDs, names, URLs, authentication details, and types. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_SANDBOXES` | List Sandboxes | Lists all sandboxes for the organization. Use this action when you need to retrieve information about all available sandboxes, including their configuration, state, labels, and resource quotas. This is a read-only operation that does not modify any resources. Optional filters can be applied to include verbose output, filter by specific labels, or include errored and deleted sandboxes in the results. |
| `DAYTONA_LIST_SANDBOXES_PAGINATED` | List Sandboxes Paginated | Lists all sandboxes with pagination support. Use when you need to retrieve a paginated list of sandboxes for an organization, with optional filtering by name, labels, state, region, CPU/memory/disk specifications, and other attributes. Supports sorting by various fields and ordering results in ascending or descending order. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_SHARED_REGIONS` | List shared regions | Tool to list all shared regions. Use when you need to retrieve information about all available shared regions, including their IDs, names, types, and associated URLs (proxy, SSH gateway, snapshot manager). This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_SNAPSHOTS` | List Snapshots | Lists all snapshots for the organization. Use this action when you need to retrieve information about all available snapshots, including their configuration, state, resource allocations, and usage information. Supports filtering by partial name match and pagination for large result sets. This is a read-only operation that does not modify any resources. |
| `DAYTONA_LIST_VOLUMES` | List Volumes | Lists all volumes in the organization. Use when you need to retrieve information about all available volumes, including their IDs, names, states, and associated organizations. This is a read-only operation that does not modify any resources. Optionally include deleted volumes by setting the includeDeleted parameter to true. |
| `DAYTONA_REPLACE_IN_FILES` | Replace In Files | Replaces text or patterns in multiple files within a sandbox. Use this action when you need to perform find-and-replace operations across multiple files in a sandbox. For each file specified, the action searches for the given pattern and replaces it with the new value. This action modifies files within the sandbox, so use with caution as changes may be difficult to revert. Consider backing up files before performing bulk replacements. |
| `DAYTONA_REPLACE_SANDBOX_LABELS` | Replace Sandbox Labels | Replaces all labels on a sandbox with a new set of key-value pairs. Use this action when you need to update or redefine the labels associated with an existing sandbox. This operation completely replaces any existing labels — the previous labels will be removed. Note: This action modifies the sandbox's labels in bulk. If you need to add or remove individual labels while preserving others, consider fetching the current labels first and constructing the complete new set. |
| `DAYTONA_RESIZE_PTY_SESSION` | Resize PTY Session | Resizes an active PTY session with new terminal dimensions. Use this action when you need to change the column and row dimensions of an existing pseudo-terminal (PTY) session within a running sandbox. This is commonly used to adjust the terminal display size to match the current viewport or user preference. The session must be active for this operation to succeed. This action is idempotent - resizing to the same dimensions is safe and will not cause errors. Note: Ensure the PTY session is active before attempting to resize it. Resizing an inactive session may result in errors. |
| `DAYTONA_REVOKE_SSH_ACCESS` | Revoke SSH Access | Revokes SSH access credentials for a sandbox environment. Use this action when you need to invalidate SSH access to a sandbox, either for a specific token or all SSH access. This is useful for security purposes when you need to immediately terminate SSH sessions or prevent further SSH connections to the sandbox. This action is irreversible — once SSH access is revoked, the tokens cannot be recovered. New SSH access must be created using the Create SSH Access action if needed. |
| `DAYTONA_SEARCH_FILES` | Search Files | [DEPRECATED] Search for files inside a sandbox toolbox. Use this action when you need to find files matching a specific pattern within a sandbox toolbox. This is a read-only operation that does not modify any resources. Note: This endpoint is deprecated. It is recommended to use alternative approaches for file search in newer integrations. |
| `DAYTONA_SET_AUTO_ARCHIVE_INTERVAL` | Set Sandbox Auto Archive Interval | Sets the auto-archive interval for a sandbox. Use this action when you need to configure how long a stopped sandbox should be retained before it is automatically archived. The interval specifies the time in minutes after the sandbox stops that the archiving process will begin. Setting interval to 0 uses the maximum interval value. This action modifies the sandbox lifecycle settings and may result in the sandbox being archived if it remains stopped beyond the configured interval. |
| `DAYTONA_SET_AUTO_DELETE_INTERVAL` | Set Auto Delete Interval | Sets the auto-delete interval for a sandbox. Use this action when you need to configure automatic deletion of a sandbox after it is stopped. The interval specifies how many minutes after stopping the sandbox before it gets deleted. Use a negative value to disable auto-delete, or 0 to delete immediately upon stopping. This action modifies the sandbox lifecycle configuration and affects when the sandbox will be permanently removed after being stopped. |
| `DAYTONA_SET_AUTOSTOP_INTERVAL` | Set Autostop Interval | Sets the auto-stop interval for a sandbox in the Daytona platform. Use this action when you need to configure how long a sandbox should run idle before automatically stopping. This helps manage resources and reduce costs by automatically stopping unused sandboxes. The interval is specified in minutes. Setting the interval to 0 disables auto-stop, allowing the sandbox to run indefinitely until manually stopped. The API returns the updated sandbox object with the new auto_stop_interval value. |
| `DAYTONA_START_COMPUTER_USE` | Start Computer Use | Starts all VNC desktop processes (Xvfb, xfce4, x11vnc, novnc) for a sandbox. Use this action when you need to start all VNC desktop processes for a sandbox to enable remote desktop access. This action starts the X virtual framebuffer (Xvfb), Xfce desktop environment, x11vnc server, and noVNC web interface. Each process will have a status indicating whether it started successfully. Note: This endpoint is deprecated. Consider using alternative methods for starting computer use processes in new implementations. |
| `DAYTONA_START_LSP_SERVER` | Start LSP Server | Starts an LSP server process inside a sandbox project. Use this action when you need to initialize an LSP (Language Server Protocol) server within a running sandbox. This enables intelligent code editing features such as auto-completion, error highlighting, and code navigation for the specified programming language and project path. Note: This endpoint is deprecated. Consider alternative approaches for LSP functionality in new implementations. This action requires the sandbox to be in a running state. |
| `DAYTONA_START_PROCESS` | Start VNC Process | Restarts a specific VNC process within a sandbox in the Daytona platform. Use this action when you need to restart a VNC process (such as xfce4) within a running sandbox. This is helpful when a desktop session becomes frozen or unresponsive. The process will be terminated and started again, which can help recover a stuck interface. Note: This endpoint is deprecated. Consider alternative approaches if available. This action is generally safe as it restarts rather than removes the process, but the sandbox should be in a running state for this operation to succeed. |
| `DAYTONA_START_SANDBOX` | Start Sandbox | Starts a sandbox in the Daytona platform. Use this action when you need to start a sandbox that is stopped or archived, making it ready for use. The sandbox will transition to a running state and be accessible for operations. This action can also be used to restore a sandbox from an archived state. |
| `DAYTONA_STOP_LSP_SERVER` | Stop LSP Server | Stops an LSP server process inside a sandbox project. Use this action when you need to stop an LSP (Language Server Protocol) server that is running inside a Daytona sandbox. This is useful for freeing up resources, restarting a stuck language server, or cleaning up when LSP features are no longer needed. Note: This endpoint is deprecated. Consider alternative approaches for LSP functionality in new implementations. This action requires the sandbox to be in a running state. |
| `DAYTONA_STOP_SANDBOX` | Stop Sandbox | Stops a running sandbox in the Daytona platform. Use this action when you need to gracefully stop a running sandbox that is no longer needed or should be temporarily shut down. The sandbox can be restarted later if needed. Note: If the sandbox does not respond to normal termination signals (SIGTERM), you can use the `force` parameter to forcibly terminate it (SIGKILL). This action is reversible — the sandbox can be restarted after being stopped. |
| `DAYTONA_TAKE_COMPRESSED_SCREENSHOT` | Take Compressed Screenshot | Takes a compressed screenshot of the entire screen in a sandbox. Use this action when you need to capture the current visual state of a sandbox's display with compression. The response includes base64-encoded image data that can be decoded to view the screenshot. Compression options include format selection (PNG or JPEG), quality settings for JPEG, and scale factor to reduce image dimensions. This is useful for monitoring sandbox activity, debugging visual issues, or capturing screen states with minimal data transfer. This is a read-only operation that does not modify any resources. |
| `DAYTONA_UNLINK_ACCOUNT` | Unlink Account | Unlinks a connected provider account (such as GitHub, GitLab, or Bitbucket) from the authenticated user's Daytona profile. Use when a user wants to remove a connected account or revoke its integration with Daytona. This action is irreversible — once an account is unlinked, it cannot be automatically reconnected without going through the OAuth flow again. |
| `DAYTONA_UPDATE_EXPERIMENTAL_CONFIG` | Update Experimental Config | Updates experimental configuration for an organization on the Daytona platform. Use this action when you need to configure experimental features such as OpenTelemetry settings for observability. The organization ID is automatically injected from the authentication context, so only the configuration object needs to be provided. |
| `DAYTONA_UPDATE_LAST_ACTIVITY` | Update Last Activity | Updates the last activity timestamp for a sandbox in the Daytona platform. Use this action when you need to keep a sandbox active by recording activity. This is useful for preventing auto-stop mechanisms from stopping sandboxes that are still in use. The action makes a POST request to update the sandbox's last activity timestamp. |
| `DAYTONA_UPDATE_ORGANIZATION_INVITATION` | Update Organization Invitation | Updates an organization invitation with new role and permissions. Use when you need to modify an existing organization invitation's role (owner or member) or assigned role permissions. This action allows administrators to update invitation settings after the invitation has been created. This is useful for changing a user's role within an organization or updating the permissions assigned to an invitation. |
| `DAYTONA_UPDATE_ORGANIZATION_OTEL_CONFIG` | Update Organization OpenTelemetry Config | Updates the OpenTelemetry configuration for an organization. Use this action when you need to configure or update the OTLP endpoint and custom headers for an organization's OpenTelemetry setup. This allows you to specify where telemetry data should be sent and any authentication headers required for the collector. Note: This action returns HTTP 204 on success with no response body. |
| `DAYTONA_UPDATE_ORGANIZATION_ROLE` | Update Organization Role | Updates an organization role with a new name, description, and permissions. Use this action when you need to modify an existing role within an organization, such as changing what the role is called, updating its description, or changing which permissions the role grants. This action is idempotent — calling it multiple times with the same parameters will produce the same result without side effects. |
| `DAYTONA_UPDATE_PUBLIC_STATUS` | Update Public Status | Updates the public visibility status of a sandbox in the Daytona platform. Use this action when you need to change whether a sandbox can be accessed publicly via its HTTP preview. Setting a sandbox to public makes it accessible to anyone with the link, while setting it to private restricts access to authenticated users within the organization only. The API returns the updated sandbox object with the new public status. |
| `DAYTONA_UPDATE_REGISTRY` | Update Docker Registry | Updates a Docker registry configuration. Use this action when you need to modify the settings of an existing Docker registry, such as updating the registry name, URL, or credentials. This is a modification operation that updates the registry's configuration on the Daytona platform. |
| `DAYTONA_UPDATE_SANDBOX_DEFAULT_LIMITED_NETWORK_EGRESS` | Update Sandbox Default Limited Network Egress | Updates the sandbox default limited network egress setting for an organization. Use this action when you need to configure whether new sandboxes should have limited network egress enabled by default within a specific organization. This action modifies organization-level settings and may affect how new sandboxes are provisioned. Existing sandboxes are not affected by this change. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Daytona MCP server provides comprehensive access to Daytona operations through Composio. Once connected, you can perform all major Daytona actions directly from OpenClaw using natural language commands.

## Complete Code

None listed.

## Conclusion

### Conclusion
You've successfully integrated Daytona with OpenClaw using Composio plugin. Now interact with Daytona directly from your terminal, Web UI, or any messenger app using natural language commands.
Key benefits of this setup:
- Seamless integration across TUI, Web UIs, and Messenger apps like Telegram, WhatsApp, Slack, etc.
- Natural language commands for Daytona operations
- Managed authentication through Composio
- Access to 20,000+ tools across 1000+ apps for cross-app workflows
- Programmatic tool calling for complex tool chaining
Next steps:
- Try asking OpenClaw to perform various Daytona operations
- Explore cross-app workflows by connecting more toolkits like Calendar, Slack, Notion, etc.
- Build complex automation scripts that leverage OpenClaw's 24/7 running capabilities

## How to build Daytona MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/daytona/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/daytona/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/daytona/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/daytona/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/daytona/framework/codex)
- [Hermes](https://composio.dev/toolkits/daytona/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/daytona/framework/cli)
- [Google ADK](https://composio.dev/toolkits/daytona/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/daytona/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/daytona/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/daytona/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/daytona/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/daytona/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [1password](https://composio.dev/toolkits/_1password) - 1Password is a password manager and digital vault for storing logins, secrets, notes, and secure documents. It helps individuals and teams protect credentials, share access safely, and reduce password risk.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Daytona MCP?

With a standalone Daytona MCP server, the agents and LLMs can only access a fixed set of Daytona tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Daytona and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with OpenClaw?

Yes, you can. OpenClaw fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Daytona tools.

### Can I manage the permissions and scopes for Daytona while using Tool Router?

Yes, absolutely. You can configure which Daytona scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Daytona data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)