Connect Railway to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Railway, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Railway + Microsoft Copilot

Let your AI look after your Railway apps: list projects, environments and services, check deployments and read their build and runtime logs, see which environment variables are set (names only), estimate usage, and redeploy or restart a service after confirming with you.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

RAILWAY_API_TOKEN

Step 1 — Get credentials

1. In Railway open Account Settings → Tokens (https://railway.com/account/tokens) and create a token. Choose No workspace for an account token that reaches all your workspaces, or pick a workspace for a workspace token limited to that workspace, which is the better choice for a team.
2. Paste the token into RAILWAY_API_TOKEN as Railway shows it, without the word Bearer, and install the connector.
3. Check the setup with railway_list_projects.

Project tokens do not work: a project token (project settings, Tokens) reaches only one environment of one project, goes in a different header and cannot list projects. Use an account or workspace token. railway_get_me works only with an account token; with a workspace token Railway answers Not Authorized.

What it does: projects with their environments and services, how each service runs (builder, start command, health check, region, replicas, domains), deployments with their build and runtime logs, the names of environment variables, and usage. A FAILED deployment usually broke while building, so the AI reads railway_get_build_logs; a CRASHED one broke while running, so it reads railway_get_deployment_logs.

Redeploy and restart ask first: railway_redeploy_deployment builds the service again and replaces the running deployment, which counts as billed usage; railway_restart_deployment stops and starts its containers without a new build. Both can briefly interrupt the service, so the AI tells you the service and environment and waits for your yes. Nothing here deletes or stops a service.

Variable values stay in Railway: railway_list_variable_names shows only which variables are set. railway_get_variable_values returns the values (passwords, keys, connection strings) and is switched off at install; turn it on only if the AI may see them. Runtime logs show whatever your app prints, so treat them as sensitive too.

Usage, not dollars: railway_get_estimated_usage and railway_get_usage return CPU in vCPU minutes, memory and volumes in GB minutes and egress in GB. The AI converts them with Railway's list prices (for example CPU at 20 dollars per vCPU per month); plan credits and discounts are not included.

Any other read: railway_graphql_query runs any query of the Railway API. Railway publishes no schema file, so railway_graphql_schema and railway_graphql_schema_url cannot load it; the AI looks types up with an introspection query instead. railway_graphql_mutation could change and delete anything the token reaches, so it is switched off at install, like railway_graphql_subscription. An admin can turn them on deliberately.

Common errors: Railway answers most problems with HTTP 200 and a message, which the connector reports as an error. Not Authorized: the token is wrong, revoked or has no access to that project (or railway_get_me was called with a workspace token). Project not found or Deployment not found: wrong id or no access. HTTP 429: the hourly request limit of your plan is used up (100 on Free, 1,000 on Hobby, 10,000 on Pro); wait.

The connector does not create, change or delete projects, services, environments, variables, domains or volumes, and it does not roll back deployments or draw metrics charts.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Railway tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Which of my Railway services has a failed or crashed latest deployment? Show me the log lines that explain why."
• "Read the build logs of the last deployment of the api service in production and tell me why the build failed."
• "Is DATABASE_URL set on the worker service in staging? Check only the variable names."
• "Estimate this month's Railway usage for the shop project and roughly what it will cost."
• "Restart the api service in production. Tell me which deployment you will restart and wait for my OK."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse