# How to connect Cloud 66 with ChatGPT

```json
{
  "title": "How to connect Cloud 66 with ChatGPT",
  "toolkit": "Cloud 66",
  "toolkit_slug": "cloud_66",
  "framework": "ChatGPT",
  "framework_slug": "chatgpt",
  "url": "https://composio.dev/toolkits/cloud_66/framework/chatgpt",
  "markdown_url": "https://composio.dev/toolkits/cloud_66/framework/chatgpt.md",
  "updated_at": "2026-11-14T06:01:13.827Z"
}
```

## Introduction

### How to connect Cloud 66 MCP with ChatGPT
[ChatGPT](https://chatgpt.com/) can take action across your apps and files, stay with a project for hours, and turn a goal into finished materials like sheets, slides, and docs, not just answers.
In this guide, I will explain the easiest and most secure way to connect your Cloud 66 account to ChatGPT via Composio Connect, so it can deploy apps, manage servers, inspect stacks, configure databases, and control users through natural language commands without ever putting your account credentials at risk.
For exact tool slugs and parameter tables, see the [tool catalog in the Composio docs](https://docs.composio.dev/toolkits/cloud_66).

## Also integrate Cloud 66 with

- [Claude Cowork](https://composio.dev/toolkits/cloud_66/framework/claude-cowork)
- [Grok Bot](https://composio.dev/toolkits/cloud_66/framework/grok-bot)
- [Hermes](https://composio.dev/toolkits/cloud_66/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/cloud_66/framework/atomic-agent)

## TL;DR

### Why use Composio over default connectors?
- Apps with read and write access. Default connectors mostly can read your data. Composio's Cloud 66 integration lets ChatGPT take actions like creating drafts, sending updates, labeling records, and more.
- 1,700+ SaaS toolkits out of the box. Composio gives you instant access to a vast catalog of pre-built connectors, from Gmail and Slack to Notion, Linear, and Salesforce.
- One MCP server for every app. Connect any of your applications on demand through a single endpoint, rather than juggling a separate server for each app.
- Smart, context-aware tool loading. Unlike traditional MCP servers that dump every available tool into the LLM context window, Composio searches for and loads only the tools relevant to the task at hand.
- Cross-app automation. Chain actions across multiple apps in a single run - fetch a thread, summarize it in Notion, and post highlights to Slack without leaving the conversation.

## Connect Cloud 66 to ChatGPT

### Prerequisites
- A ChatGPT account. We will use the [ChatGPT desktop app](https://openai.com/chatgpt/download/), and the steps are the same on the web.
- Access to the Cloud 66 workspace you want to connect.
- [Composio plugin](https://dashboard.composio.dev/login?cta_placement=toolkit-framework-chatgpt-composio-connect&next=%2F~%2Forg%2Fconnect%2Fclients%2Fchatgpt).
Note: Composio connects through OAuth. You will be asked to sign in and approve specific permissions. Review the permission screen carefully if you are using a work account.
### Step-by-step: Connect Cloud 66 to ChatGPT
### 1. Install the Composio plugin
Click the button. ChatGPT opens the Composio plugin page. Click Install plugin.
[Install in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6a58503580c08191b78cc5bdaf4eba6e)
You can also find it inside ChatGPT: go to Settings, open Plugins, search the marketplace for Composio, and click Install plugin.
### 2. Authenticate
After you install, ChatGPT asks you to authenticate with Composio. Log in and click Allow access to authorize ChatGPT to use your Composio account.
### 3. Start using Composio
That is it. Composio tools are now available in ChatGPT. Type @Composio followed by your request, for example @Composio find unread Cloud 66 messages and summarize them, and it will run the actions you authorize. On first use it asks you to authorize Cloud 66.
### Option 2: Add Composio as an MCP server
If you cannot use the plugin marketplace, add Composio as a custom MCP server instead.
### 1. Open the MCP settings
In ChatGPT, go to Settings and open the Plugins section. Inside the Plugins page, click the MCP tab.
### 2. Add the server
Click Add server. In the Name field enter Composio, for Type select Streamable HTTP, and in the URL field paste the Composio MCP server URL:

```bash
https://connect.composio.dev/mcp
```

## What is the Cloud 66 MCP server, and what's possible with it?

The Cloud 66 MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloud 66 account. It provides structured and secure access to Cloud 66 deployment, infrastructure, database, networking, backup, and account operations, so your agent can create and manage stacks, inspect or cancel deployments, provision databases, configure networking and SSL, and monitor servers and containers on your behalf.
- Stack and deployment management: Have your agent create Docker stacks, check deployment details, cancel active deployments, clear stack caches, and manage application variants.
- Database operations: Let the agent create or delete databases, create and remove database users, and disable replication when needed.
- Networking and security: Direct your agent to create firewall rules, set up gateways, create or delete elastic addresses, and request or remove SSL certificates for your stacks.
- Infrastructure visibility: Instruct your agent to inspect cloud regions and server sizes, review server and server setting details, check cluster health, and retrieve container or process information.
- Backups and account access: Have your agent create scheduled backup tasks, retrieve backup details and download links, verify the current Cloud 66 identity, and manage registered user devices.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CLOUD_66_ADD_USER_DEVICE` | Add User Device | Register a human user's mobile device token with Cloud 66. This changes the user's UI notification destination. Cloud 66 currently supports iOS devices; Android is documented but not currently available. |
| `CLOUD_66_CANCEL_DEPLOYMENT` | Cancel Deployment | Cancel an existing Cloud 66 deployment. This irreversibly stops the deployment operation but does not delete its deployment history. |
| `CLOUD_66_CLEAR_STACK_CACHES` | Clear Stack Caches | Clear all application caches for a Cloud 66 stack and return the accepted asynchronous job by default. Cache removal cannot be undone. |
| `CLOUD_66_COMMIT_APPLICATION_VARIANT` | Commit Application Variant | Finalize a rollout application variant and make it the active production version. This immediately changes which application version serves production traffic and cannot be undone by this action. |
| `CLOUD_66_CREATE_BACKUP_TASK` | Create Backup Task | Create a scheduled backup task for a Cloud 66 stack. Cloud 66 only acknowledges that the task was queued; this action does not wait for or claim backup completion. |
| `CLOUD_66_CREATE_CLUSTER` | Create Cluster | Call Cloud 66's documented cluster-creation route with no parameters. Cloud 66 currently documents this operation as unavailable and returning HTTP 501 Not Implemented; this action reports that condition as an error, not success. |
| `CLOUD_66_CREATE_CONTAINER_SESSION` | Create Container Session | Start an interactive Cloud 66 container session. A successful result confirms only that the asynchronous action was accepted; it does not confirm that the session is ready. |
| `CLOUD_66_CREATE_DATABASE` | Create Database | Create a database in a Cloud 66 server group, optionally grant database users access, and by default wait for asynchronous completion. |
| `CLOUD_66_CREATE_DATABASE_USER` | Create Database User | Create a database user in a Cloud 66 server group. By default, wait for the asynchronous action to finish and return only after Cloud 66 reports successful completion. |
| `CLOUD_66_CREATE_ELASTIC_ADDRESS` | Create Elastic Address | Create an elastic address failover group between distinct primary and secondary Cloud 66 stacks. |
| `CLOUD_66_CREATE_FIREWALL_RULE` | Create Firewall Rule | Add a firewall rule to a Cloud 66 stack using a numeric protocol code and at least one destination field. Returns the accepted asynchronous action; the action ID is not the created firewall-rule ID. |
| `CLOUD_66_CREATE_GATEWAY` | Create Gateway | Create a gateway for a Cloud 66 account using bastion-server connection metadata without accepting private-key content. Cloud 66 confirms success without returning the new gateway ID; call CLOUD_66_LIST_GATEWAYS afterward. |
| `CLOUD_66_CREATE_SSL_CERTIFICATE` | Create SSL Certificate | Submit a Let's Encrypt SSL-certificate creation request for a Cloud 66 stack. Manual certificate and private-key uploads are excluded. A successful result confirms request acceptance only, not completed certificate provisioning. |
| `CLOUD_66_CREATE_STACK` | Create Stack | Create and build a Docker stack. A non-terminal result confirms acceptance only because Cloud 66 does not return a documented stack UID that can safely route action-status polling. |
| `CLOUD_66_DELETE_ALL_TAGS` | Delete All Tags | Permanently delete all tags from one Cloud 66 server or load balancer. This removes the entity's entire tag set, not one selected tag, and cannot be undone; verify the entity type and ID first. |
| `CLOUD_66_DELETE_APPLICATION_VARIANT` | Delete Application Variant | Permanently delete a preview application variant from a Cloud 66 stack. This operation only applies to preview variants and cannot be undone. |
| `CLOUD_66_DELETE_DATABASE` | Delete Database | Permanently delete a Cloud 66 database and all of its data. This cannot be undone. By default, wait for the asynchronous action to finish and fail unless Cloud 66 confirms successful completion. |
| `CLOUD_66_DELETE_DATABASE_USER` | Delete Database User | Permanently remove a database user from every associated database. This cannot be undone. By default, wait for Cloud 66's asynchronous deletion to finish and fail if the terminal action reports failure. |
| `CLOUD_66_DELETE_ELASTIC_ADDRESS` | Delete Elastic Address | Permanently delete a Cloud 66 elastic address (failover group). This cannot be undone. The failover group must be detached from all stacks before deletion. |
| `CLOUD_66_DELETE_ENVIRONMENT_VARIABLE` | Delete Environment Variable | Permanently delete an environment variable from a Cloud 66 stack by its key/name. This irreversible operation cannot recover the deleted value; verify the stack UID and key before calling it. |
| `CLOUD_66_DELETE_GATEWAY` | Delete Gateway | Permanently delete a gateway from a Cloud 66 account. This irreversible operation cannot be undone; verify both the account ID and gateway ID first. |
| `CLOUD_66_DELETE_SSL_CERTIFICATE` | Delete SSL Certificate | Permanently delete an SSL certificate from a Cloud 66 stack. Verify the stack and certificate identifiers before this irreversible operation. A successful result confirms request acceptance only, not completed removal. |
| `CLOUD_66_DISABLE_DATABASE_REPLICATION` | Disable Database Replication | Disable replication to a Cloud 66 slave database server and return the accepted irreversible asynchronous job by default. |
| `CLOUD_66_GET_ACCOUNT` | Get Account | Retrieve detailed information for a specific Cloud 66 account. |
| `CLOUD_66_GET_API_STATUS` | Get API Status | Call Cloud 66's unauthenticated basic ping endpoint and return its acknowledgement. A successful response confirms only that this endpoint answered; it does not validate the connected OAuth account or guarantee broader API availability. |
| `CLOUD_66_GET_BACKUP` | Get Backup | Get information about a single Cloud 66 backup. |
| `CLOUD_66_GET_BACKUP_FILE` | Get Backup File | Get the public download URL for a Cloud 66 backup file. |
| `CLOUD_66_GET_CLOUD` | Get Cloud | Get regions and server sizes for one cloud provider available to the connected Cloud 66 account. |
| `CLOUD_66_GET_CLOUD_REFERENCE` | Get Cloud Reference | Return Cloud 66 cloud-provider reference data needed to select valid cloud, region, and server-size values. Use cloud and filter to limit the response. |
| `CLOUD_66_GET_CLUSTER` | Get Cluster | Return status, health, capacity, and node details for a Kubernetes cluster. |
| `CLOUD_66_GET_CONTAINER` | Get Container | Get runtime information for a specific container in a Cloud 66 stack. |
| `CLOUD_66_GET_CONTAINER_SESSION` | Get Container Session | Get a specific Cloud 66 container session by session ID, or the most recent session for a service. Requires SSH key download permission on the stack. |
| `CLOUD_66_GET_CURRENT_IDENTITY` | Get Current Identity | Verify the Cloud 66 connection and return the authenticated user and current account identity. |
| `CLOUD_66_GET_DEPLOYMENT` | Get Deployment | Get information about a single deployment in a Cloud 66 stack. |
| `CLOUD_66_GET_ENVIRONMENT_VARIABLE` | Get Environment Variable | Get one environment variable's name and metadata from a Cloud 66 stack by numeric ID. Current and historical values are never returned. |
| `CLOUD_66_GET_FIREWALL_RULE` | Get Firewall Rule | Get information about a specific firewall rule in a Cloud 66 stack. |
| `CLOUD_66_GET_NGINX_MODULE_REFERENCE` | Get Nginx Module Reference | Return the Nginx modules supported by Cloud 66 stack configuration. |
| `CLOUD_66_GET_PROCESS` | Get Process | Gets one page of information about a specific process in a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_GET_SERVER` | Get Server | Get information about a single server in a Cloud 66 stack. |
| `CLOUD_66_GET_SERVER_SETTING` | Get Server Setting | Get information about a single setting for a server in a Cloud 66 stack. |
| `CLOUD_66_GET_SSL_CERTIFICATE` | Get SSL Certificate | Get one SSL certificate from a Cloud 66 stack by certificate identifier. |
| `CLOUD_66_GET_STACK` | Get Stack | Retrieve detailed configuration, deployment status, and health for a Cloud 66 stack. |
| `CLOUD_66_GET_STACK_ACTION` | Get Stack Action | Return the current state and result of one asynchronous Cloud 66 stack action. |
| `CLOUD_66_GET_STACK_ALERT` | Get Stack Alert | Return the configuration for a named alert on a Cloud 66 stack. |
| `CLOUD_66_GET_STACK_SETTING` | Get Stack Setting | Get a single setting for a Cloud 66 stack by its setting identifier. |
| `CLOUD_66_GET_USER` | Get User | Get detailed information about a Cloud 66 user by user ID. |
| `CLOUD_66_IMPORT_BACKUP` | Import Backup | Queue an external backup import for a Cloud 66 stack. Cloud 66 only acknowledges that the import was queued; this action does not wait for or claim import completion. |
| `CLOUD_66_LIST_ACCOUNTS` | List Accounts | Lists accounts that the current authenticated user can access. Each call returns one page, normally up to 30 items. |
| `CLOUD_66_LIST_APPLICATION_VARIANTS` | List Application Variants | Returns all active, rollout, and preview application variants for a specified Cloud 66 stack. |
| `CLOUD_66_LIST_BACKUP_FILES` | List Backup Files | Get backup files for a Cloud 66 stack backup. Each call returns one page, normally up to 30 items. |
| `CLOUD_66_LIST_BACKUPS` | List Backups | Gets backups for a Cloud 66 stack. Each call returns one page, normally up to 30 items. |
| `CLOUD_66_LIST_CLOUDS` | List Clouds | Get cloud providers available to the connected Cloud 66 account, with their regions and server sizes. Each call returns one page, normally up to 30 items. |
| `CLOUD_66_LIST_CLUSTERS` | List Clusters | Return one documented page of Kubernetes clusters accessible to the user. Each call returns one page, currently up to 100 clusters. This documented route returned an HTML 404 in prior probing, so availability may depend on the account or provider deployment. |
| `CLOUD_66_LIST_CONTAINERS` | List Containers | Gets containers for a Cloud 66 stack, optionally filtered by server. Each call returns one page, normally up to 30 items. |
| `CLOUD_66_LIST_DATABASES` | List Databases | Returns one page of databases associated with a Cloud 66 server group; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_DATABASE_USERS` | List Database Users | Gets one page of database-user names and metadata for a Cloud 66 server group. Passwords and password hashes are never requested or returned. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_DEPLOYMENTS` | List Deployments | Gets one page of deployments for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_DNS_PROVIDERS` | List DNS Providers | Gets one page of DNS providers configured for SSL certificate management; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_ELASTIC_ADDRESSES` | List Elastic Addresses | Return Cloud 66's documented elastic-address failover groups. This documented route returned an HTML 404 in prior probing without a scope or paid-tier signal, so its availability is unresolved. |
| `CLOUD_66_LIST_ENVIRONMENT_VARIABLES` | List Environment Variables | Get one page of environment-variable names and metadata for a Cloud 66 stack. Current and historical values are never returned. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_FIREWALL_RULES` | List Firewall Rules | Gets one page of firewall rules for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_GATEWAYS` | List Gateways | Gets one page of gateway metadata for a Cloud 66 account. Private-key content is never returned. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_IMAGE_REPOSITORIES` | List Image Repositories | Gets one page of image repositories for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_JOBS` | List Jobs | Gets one page of jobs configured on a Cloud 66 stack, including each job's command and run_on server-target context. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_NOTIFICATIONS` | List Notifications | Return one documented page of Cloud 66 notification records. Each call returns one page, normally up to 30 items. This documented route returned an HTML 404 in prior probing, so availability may depend on the account or provider deployment. |
| `CLOUD_66_LIST_PROCESSES` | List Processes | Gets one page of processes for a Cloud 66 stack, optionally filtered by server; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_SERVER_GROUPS` | List Server Groups | Gets one page of server groups for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_SERVERS` | List Servers | Gets one page of servers for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_SERVER_SETTINGS` | List Server Settings | Returns one page of settings for a server, including optional IDs, timestamps, and warnings when Cloud 66 provides them; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_SERVICES` | List Services | Gets one page of services for a Cloud 66 stack; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_SSL_CERTIFICATES` | List SSL Certificates | Gets one page of SSL certificate metadata for a Cloud 66 stack. Certificate and private-key material is never returned. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_STACK_ACTIONS` | List Stack Actions | Retrieve one page of asynchronous actions performed for a Cloud 66 stack, optionally filtered by caller reference; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_STACK_ALERTS` | List Stack Alerts | Returns the alert configurations and notification channels for a specified stack. |
| `CLOUD_66_LIST_STACKS` | List Stacks | Retrieves stack objects accessible to the current user. Each call returns one page, currently up to 100 stacks. |
| `CLOUD_66_LIST_STACK_SETTINGS` | List Stack Settings | Returns one page of settings for a Cloud 66 stack, including their values and read-only status; Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_TAGS` | List Tags | Gets one page of tags for a Cloud 66 server or load balancer, identified by entity type and ID. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_LIST_USERS` | List Users | Gets one page of users in the connected Cloud 66 account, including account roles and access-profile details when available. Cloud 66 normally returns up to 30 items per page. |
| `CLOUD_66_PATCH_SSL_CERTIFICATE` | Patch SSL Certificate | Update a Let's Encrypt SSL certificate using Cloud 66's PATCH method. Manual certificate and private-key uploads are excluded. Cloud 66 does not distinguish PATCH from PUT semantics. Success confirms request acceptance only. |
| `CLOUD_66_PAUSE_WORKLOAD` | Pause Stack Workload | Pause a Cloud 66 service or process workload. Services require service_name, server_uid, or both; processes require process_name, server_uid, or both. By setting all_workloads=true without either selector, the action broadly pauses every workload of the selected type across the stack. Pausing workloads is disruptive; the accepted asynchronous job is returned by default. |
| `CLOUD_66_PROMOTE_DATABASE_REPLICA` | Promote Database Replica | Promote a Cloud 66 slave database server to a standalone master and return the accepted irreversible asynchronous job by default. |
| `CLOUD_66_PUT_SSL_CERTIFICATE` | Put SSL Certificate | Update a Let's Encrypt SSL certificate using Cloud 66's PUT method. Manual certificate and private-key uploads are excluded. Cloud 66 does not distinguish PUT from PATCH semantics. Success confirms request acceptance only. |
| `CLOUD_66_REBOOT_CLUSTER_SERVERS` | Reboot Cluster Servers | Queue an irreversible reboot of selected Kubernetes cluster servers. A non-terminal result confirms acceptance only because Cloud 66 does not return a documented stack UID that can safely route action-status polling. |
| `CLOUD_66_REBOOT_SERVER` | Reboot Server | Initiate an irreversible reboot of one Cloud 66 server. A successful result confirms acceptance only; this endpoint does not confirm that the server finished rebooting. |
| `CLOUD_66_REBOOT_STACK_SERVERS` | Reboot Stack Servers | Reboot all servers or one server group in a Cloud 66 stack using a parallel or serial strategy, and by default wait for documented asynchronous completion. |
| `CLOUD_66_REDEPLOY_STACK` | Redeploy Stack | Redeploy a Cloud 66 stack. This changes its running deployment and returns the accepted asynchronous action by default because deployments commonly outlast the tool execution window. |
| `CLOUD_66_REPLACE_TAGS` | Replace Tags | Replace all tags on one Cloud 66 server or load balancer with the supplied non-empty tag set. |
| `CLOUD_66_RESTART_STACK` | Restart Stack | Restart every component of a Cloud 66 stack and return the accepted asynchronous job by default. The restart is disruptive. |
| `CLOUD_66_RESTART_WORKLOAD` | Restart Stack Workload | Restart a Cloud 66 container, service, or process workload. Containers require container_id. Services require service_name, server_uid, or both; processes require process_name, server_uid, or both. Set all_workloads=true without either selector to restart every workload of the selected type across the stack. Restarts are disruptive and irreversible once initiated; the accepted asynchronous job is returned by default. |
| `CLOUD_66_RESUME_WORKLOAD` | Resume Stack Workload | Resume a Cloud 66 service or process workload. Services require service_name, server_uid, or both; processes require process_name, server_uid, or both. By setting all_workloads=true without either selector, the action broadly resumes every workload of the selected type across the stack. Resuming workloads is disruptive; the accepted asynchronous job is returned by default. |
| `CLOUD_66_RESYNC_DATABASE_REPLICA` | Resync Database Replica | Re-synchronize a PostgreSQL or MySQL Cloud 66 slave database server with its master and return the accepted asynchronous job by default. The replica's current data may be replaced. |
| `CLOUD_66_SCALE_PROCESS` | Scale Process | Trigger the provider-configured scaling operation for a process on a Cloud 66 stack and, by default, poll until Cloud 66 confirms success. This tool cannot set a desired process count; scaling behavior comes from the process's existing Cloud 66 configuration. |
| `CLOUD_66_SET_STACK_MAINTENANCE_MODE` | Set Stack Maintenance Mode | Enable or disable maintenance mode for a Cloud 66 stack. By default this returns the accepted asynchronous job because Cloud 66 can take 70-120 seconds to mark it complete. |
| `CLOUD_66_STOP_CONTAINER` | Stop Container | Stop a container in a Cloud 66 stack. This changes the container's running state and can interrupt workloads. |
| `CLOUD_66_UPDATE_APPLICATION_GROUP_ALERTS` | Update Application Group Alerts | Apply alert configurations to every stack in a Cloud 66 application group and report successes, non-applicable alerts, and failures. |
| `CLOUD_66_UPDATE_APPLICATION_VARIANT_PERCENTAGE` | Update Application Variant Percentage | Change the percentage of production traffic sent to a canary rollout application variant. This action applies only to canary deployments. |
| `CLOUD_66_UPDATE_ELASTIC_ADDRESS` | Update Elastic Address | Update an elastic address's primary or secondary stack assignment, or switch which stack currently receives traffic. Provide at least one of primary_stack_uid, secondary_stack_uid, or current_stack. |
| `CLOUD_66_UPDATE_GATEWAY` | Update Gateway | Update a Cloud 66 gateway's bastion-server metadata without accepting or returning private-key content. Provide at least one of name, username, address, ttl, or private_ip. |
| `CLOUD_66_UPDATE_SERVER_SETTING` | Update Server Setting | Update one server setting in a Cloud 66 stack and, by default, poll the asynchronous action until Cloud 66 confirms success. |
| `CLOUD_66_UPDATE_STACK_ALERTS` | Update Stack Alerts | Update one or more Cloud 66 stack alert configurations. Only specified alerts are changed; other stack alert settings remain unchanged. |
| `CLOUD_66_UPDATE_STACK_SETTING` | Update Stack Setting | Update one Cloud 66 stack setting and, by default, poll the asynchronous action until Cloud 66 confirms success. |
| `CLOUD_66_UPDATE_TAGS` | Update Tags | Incrementally add or delete tags on one Cloud 66 server or load balancer. Deleting a tag that is not present is ignored; Cloud 66 performs deletions before additions. |
| `CLOUD_66_UPDATE_USER` | Update User | Update a Cloud 66 user's access profile. This changes account permissions and stack roles for a human user; verify the target user and intended access before calling. Cloud 66 ignores user fields outside access_profile. |

## Supported Triggers

None listed.

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

Once connected, ChatGPT can access the Cloud 66 MCP server via Composio to run actions that you authorize, directly in your workspace.

## Complete Code

None listed.

## How to build Cloud 66 MCP Agent with another framework

- [Claude Cowork](https://composio.dev/toolkits/cloud_66/framework/claude-cowork)
- [Grok Bot](https://composio.dev/toolkits/cloud_66/framework/grok-bot)
- [Hermes](https://composio.dev/toolkits/cloud_66/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/cloud_66/framework/atomic-agent)

## 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.
- [Agent37](https://composio.dev/toolkits/agent37) - Agent37 is a control API for managed agent sandboxes, templates, networking, and execution. It gives teams built-in scheduling, observability, budgets, and workspace administration.
- [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.
- [Anakin](https://composio.dev/toolkits/anakin_io) - Anakin is a web automation platform offering scraping, crawling, search, and browser automation. Use it to extract structured data, automate site tasks, and monitor web changes reliably.
- [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.
- [AnyAPI](https://composio.dev/toolkits/anyapi) - AnyAPI is a marketplace of utility APIs for validation, currency conversion, holidays, documents, and web data. It brings common application workflows together through one practical API platform.
- [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.
- [Authyo](https://composio.dev/toolkits/authyo) - Authyo is a REST API service for passwordless authentication, OTP verification, session management, and transactional notifications. Use it to add secure login flows and user verification without building auth infrastructure from scratch.
- [AWS Marketplace MCP](https://composio.dev/toolkits/aws_marketplace_mcp) - AWS Marketplace MCP provides MCP access to AWS Marketplace's cloud software, data, and services catalog. Use it to discover, compare, and evaluate 30K+ AWS Marketplace listings faster.
- [Azure DevOps](https://composio.dev/toolkits/azure_devops) - Azure DevOps is Microsoft's platform for planning work, managing code, and delivering software. It helps development teams collaborate and ship applications with connected tools.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Cloud 66 MCP?

With a standalone Cloud 66 MCP server, the agents and LLMs can only access a fixed set of Cloud 66 tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Cloud 66 and many other apps based on the task at hand, all through a single MCP endpoint.

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

Yes, you can. ChatGPT 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 Cloud 66 tools.

### Can I manage the permissions and scopes for Cloud 66 while using Tool Router?

Yes, absolutely. You can configure which Cloud 66 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 Cloud 66 data and credentials are handled as safely as possible.

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