Skip to main content
mcp-c is in open beta. Share feedback via GitHub or Discord.

​
TL;DR

That is enough to put any MCP application—mcp-agent workflow, FastMCP server, or ChatGPT App backend—online. Deployments automatically run on the managed Temporal cluster; you do not need to configure Temporal hosts or queues yourself. The sections below add a little context and point to deeper guides when you are ready.

​
1. Authenticate (one time)

The CLI opens a browser window so you can sign in with GitHub or Google and generate an API key. Credentials are cached under ~/.mcp-agent/credentials.json. In CI, set the MCP_API_KEY environment variable instead.

​
2. Confirm your project layout

Minimal structure:
mcp_agent.config.yaml just needs to describe your app. You can keep execution_engine: temporal if you already use it locally, but the cloud service will always launch your code on Temporal automatically. Example:
mcp_agent.config.yaml
If your app needs API keys, either place them in mcp_agent.secrets.yaml or declare them in the env list inside mcp_agent.config.yaml so the CLI captures values from your shell. See Manage secrets for full guidance.

​
3. Deploy

The CLI bundles the current directory, prompts you to classify secrets (deployment vs. user), uploads the bundle, and provisions the runtime. On success you will see something like:
Redeploy with the same name to ship updates. Useful flags:
  • --config-dir <path> – deploy from another directory.
  • --non-interactive – reuse stored secrets (CI/CD).
  • --dry-run – validate without uploading.
Deployment emits both mcp_agent.deployed.secrets.yaml (secret handles and env references) and mcp_agent.deployed.config.yaml (materialized settings). Commit them if you want reproducible bundles.

​
4. Check status & logs

describe prints the endpoint, auth mode, and worker status. logger tail streams application logs; add --since 30m or --grep "ERROR" as needed. All other operational commands are listed on the cloud overview.

​
5. Configure clients

Most deployments need per-user credentials. Prompt users (or your CI job) with:
Then install the server into your favourite MCP client:
  • Claude Desktop / Cursor / VS Code / ChatGPT – uvx mcp-agent install --client <client> https://app_abc123xyz.deployments.mcp-agent.com/sse
  • ChatGPT Apps – deploy with --no-auth and register the SSE endpoint in the Apps dashboard.
  • Python – add the server endpoint to your MCP client config (see guide).
To inspect or rotate deployment-time environment secrets later, use uvx mcp-agent cloud env list|add|remove|pull. These commands operate on the same handles created during deploy and are safe to run from CI.

​
Going further