# How to integrate Railway MCP with Atomic Agent

```json
{
  "title": "How to integrate Railway MCP with Atomic Agent",
  "toolkit": "Railway",
  "toolkit_slug": "railway",
  "framework": "Atomic Agent",
  "framework_slug": "atomic-agent",
  "url": "https://composio.dev/toolkits/railway/framework/atomic-agent",
  "markdown_url": "https://composio.dev/toolkits/railway/framework/atomic-agent.md",
  "updated_at": "2026-09-16T08:04:50.541Z"
}
```

## Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Railway.
This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Railway account. See the [Atomic Agent documentation](https://atomicagent.io/docs/?cta_placement=atomic-agent-docs) for installation instructions.

## Also integrate Railway with

- [ChatGPT](https://composio.dev/toolkits/railway/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/railway/framework/claude-cowork)
- [Grok Bot](https://composio.dev/toolkits/railway/framework/grok-bot)
- [Codex](https://composio.dev/toolkits/railway/framework/codex)
- [Cursor](https://composio.dev/toolkits/railway/framework/cursor)
- [Hermes](https://composio.dev/toolkits/railway/framework/hermes-agent)

## TL;DR

### How Atomic Agent connects to Railway
Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.
Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

## Connect Railway to Atomic Agent

### Connect Railway to Atomic Agent
- Sign up or sign in to the [Composio dashboard](https://dashboard.composio.dev/?cta_placement=atomic-agent-api-key). Copy your API key.
- In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
- Ask Atomic Agent to do something in Railway. It searches Composio for the right tool.
- On first use, open the sign-in link returned in the chat. Connect your Railway account, then return to Atomic Agent to continue.
### Headless setup
Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

```bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY
```

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

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

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `RAILWAY_CREATE_PLUGIN` | Create Plugin | Creates a new plugin in Railway for the specified project. Use this action when you need to add a custom plugin to a Railway project, such as for integrating external services or extending project functionality. The action requires a valid project ID (found in the Railway dashboard URL) and a descriptive name for the plugin. The plugin will be created with default settings and can be further configured after creation. |
| `RAILWAY_DELETE_VARIABLE` | Delete Variable | Delete a Railway environment variable. This action uses the `variableDelete` GraphQL mutation to permanently remove an environment variable from a project, environment, or service. This action is irreversible — once deleted, the variable cannot be recovered. |
| `RAILWAY_DELETE_VOLUME` | Delete Volume | Permanently delete a persistent volume and all its associated data from Railway. Use when you need to remove a volume that is no longer needed. This action is irreversible — the volume and all its data will be permanently deleted and cannot be recovered once removed. Use this action when: - Cleaning up unused volumes to reduce storage costs - Removing volumes associated with deprecated environments - Deleting volumes before removing a project |
| `RAILWAY_DELETE_WORKSPACE` | Delete workspace | Delete a Railway workspace and all data associated with it. This action uses the `workspaceDelete` GraphQL mutation to permanently remove a workspace. Use this action when you need to permanently delete a workspace that is no longer needed. This action is irreversible — once deleted, the workspace and all its associated projects, environments, and data cannot be recovered. |
| `RAILWAY_DISCONNECT_USER_DISCORD` | Disconnect Discord account | Disconnects the authenticated user's Railway account from Discord. Use when you need to unlink a Discord account that was previously connected to Railway for notifications, authentication, or team management. This action is irreversible for the disconnect operation — the user must manually reconnect through the Railway dashboard or Discord OAuth flow if needed. |
| `RAILWAY_GET_DEPLOYMENT_LOGS` | Get Deployment Logs | Retrieve runtime logs for a deployment. Use when you need to view the runtime application logs for troubleshooting runtime issues, monitoring application behavior, or debugging errors that occur during deployment execution. This action queries the Railway GraphQL API for runtime log entries associated with the specified deployment ID. The logs are returned in reverse chronological order (most recent first). |
| `RAILWAY_GET_ENVIRONMENT` | Get Environment | Get details of a specific Railway environment by its ID, including service instances and deployment information. Use this action when you need to retrieve detailed information about an environment, such as its name, creation timestamp, and the service instances deployed within it, along with their latest deployment statuses. This is a read-only action that queries the Railway GraphQL API. |
| `RAILWAY_GET_GIT_HUB_PR_INFO` | Get GitHub PR Info | Get information for a GitHub pull request associated with a Railway service. Use this action when you need to retrieve details about a specific pull request, such as its title, state, URL, or author information, for monitoring PR status or integrating with CI/CD workflows. This is a read-only action that queries the Railway GraphQL API for pull request information linked to the specified service. |
| `RAILWAY_GET_USER_KICKBACK_EARNINGS` | Get User Kickback Earnings | Get the total kickback earnings for the authenticated Railway user. Use this action when you need to retrieve the kickback earnings information for the authenticated user, including the total amount earned and the currency. This is a read-only operation that queries the Railway GraphQL API. Kickback earnings are rewards earned through the Railway referral program when users you refer upgrade their Railway projects. |
| `RAILWAY_LIST_API_TOKENS` | List API Tokens | Retrieve all API tokens for the authenticated user from Railway. Use this action when you need to fetch the list of API tokens associated with the currently authenticated user. This is a read-only operation that returns token metadata including the ID, name, and creation timestamp for each token. The action queries the Railway GraphQL API and returns the complete list of tokens. |
| `RAILWAY_LIST_ENVIRONMENT_PATCHES` | List Environment Patches | Retrieve all patches for a Railway environment using the GraphQL API. Use this action when you need to fetch the list of configuration patches applied to an environment. This is useful for auditing environment history, tracking configuration changes, or reviewing past deployments to an environment. The action queries the Railway GraphQL API for all patches associated with the specified environment ID and returns their metadata including identifiers and timestamps. |
| `RAILWAY_LIST_GIT_HUB_REPOS` | List GitHub Repos | Retrieve a list of GitHub repositories that Railway has access to. Use this action when you need to fetch the list of GitHub repositories associated with the authenticated user's GitHub account through Railway. This is a read-only operation that returns the id, name, and owner for each repository. The action queries the Railway GraphQL API githubRepos endpoint and returns the complete list of accessible GitHub repositories. |
| `RAILWAY_LIST_GIT_HUB_WRITABLE_SCOPES` | List GitHub Writable Scopes | Retrieve the list of GitHub scopes the user has installed the installation to. Use this action when you need to fetch the list of GitHub scope names that the authenticated user has granted to the Railway GitHub application. This is a read-only operation that returns an array of GitHub permission scope strings such as 'repo', 'workflow', or 'read:user'. Note: This endpoint requires account-level authentication, not workspace/project tokens. |
| `RAILWAY_LIST_INTEGRATION_AUTHS` | List Integration Auths | Retrieve all integration auths for the authenticated user from Railway. Use this action when you need to fetch the list of integration auths (such as GitHub, GitLab, Vercel, or other connected integrations) associated with the currently authenticated user. This is a read-only operation that returns auth metadata including the ID, name, type, and creation timestamp for each integration. The action queries the Railway GraphQL API and returns the complete list of integration auths. |
| `RAILWAY_LIST_NOTIFICATION_DELIVERIES` | List Notification Deliveries | Retrieve notification deliveries for the authenticated user. Use this action when you need to fetch a list of notification deliveries, such as tracking which notifications have been sent (e.g., EMAIL, WEBHOOK, SLACK) and when they were created. This is a read-only operation that queries the Railway GraphQL API. The action supports pagination through the GraphQL edges/node pattern and returns basic notification delivery information including ID, type, and creation timestamp for each delivery. |
| `RAILWAY_LIST_TRUSTED_DOMAINS` | List Railway Trusted Domains | Fetch all trusted domains for the authenticated Railway workspace. Use this action when you need to retrieve all trusted domains configured for workspace membership invitations. Trusted domains allow users with emails from those domains to be invited to the workspace without individual invitations. This is useful for auditing existing domain configurations or obtaining domain IDs for deletion operations. This action requires authentication and will return domains from the workspace associated with the provided credentials. |
| `RAILWAY_UPDATE_PROJECT` | Update Project | Update project settings and configuration on Railway. Use this action when you need to modify project properties such as description, visibility settings, or PR deploy preferences. The following fields can be updated: - description: A brief description of the project - isPublic: Whether the project is publicly visible - prDeploys: Whether pull request preview deployments are enabled This is an idempotent operation — updating a project with the same settings multiple times will not change the result after the first update. |
| `RAILWAY_UPDATE_SERVICE_INSTANCE` | Update Service Instance | Update build/deploy settings for a service in a specific environment on Railway. Use this action when you need to modify service configuration including commands, healthcheck, replicas, region, and cron schedule. This is an idempotent operation. The following fields can be updated: - startCommand: Custom start command for the service - buildCommand: Custom build command - rootDirectory: Root directory for monorepo setups - healthcheckPath: Health check endpoint path - healthcheckTimeout: Health check timeout in seconds - region: Deployment region - numReplicas: Number of service replicas - restartPolicyType: Restart policy (ON_FAILURE, ALWAYS, NEVER) - restartPolicyMaxRetries: Maximum restart retries - cronSchedule: Cron expression for scheduled deployments - sleepApplication: Enable/disable sleep when idle - dockerfilePath: Custom Dockerfile path - watchPatterns: File patterns for automatic redeployment |

## Supported Triggers

None listed.

## Troubleshooting

### Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

### Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

### Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See [Composio pricing](/pricing) for the current limits that apply to your connection.

## Complete Code

None listed.

## Conclusion

### Use Railway from Atomic Agent
With your account connected, ask Atomic Agent to work with Railway in natural language. You can connect more apps through the same Composio integration as you need them.
Visit the [Atomic Agent website](https://atomicagent.io/?cta_placement=atomic-agent-site) or inspect the [Atomic Agent source code](https://github.com/AtomicBot-ai/atomic-agent?cta_placement=atomic-agent-repo).

## How to build Railway MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/railway/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/railway/framework/claude-cowork)
- [Grok Bot](https://composio.dev/toolkits/railway/framework/grok-bot)
- [Codex](https://composio.dev/toolkits/railway/framework/codex)
- [Cursor](https://composio.dev/toolkits/railway/framework/cursor)
- [Hermes](https://composio.dev/toolkits/railway/framework/hermes-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.
- [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.
- [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 Monitor Activity Log](https://composio.dev/toolkits/azure_monitor_activity_log) - Azure Monitor Activity Log is Azure's service that records management and control-plane events for a subscription. Use it to audit changes, troubleshoot issues, and track resource operations across your Azure resources.
- [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.

## Frequently Asked Questions

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

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

### Can I use Tool Router MCP with Atomic Agent?

Yes, you can. Atomic Agent 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 Railway tools.

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

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

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