MCP server for agents

The Meticulous MCP server is a hosted Model Context Protocol endpoint that exposes the same read, analysis, and test-run-triggering operations as the agent CLI commands, available as tools your coding agent can call directly instead of shelling out to the CLI. It is hosted at:

https://app.meticulous.ai/api/mcp

Connecting a client (zero config)

The server is an OAuth 2.1 protected resource, so clients connect with just the endpoint URL. Login happens in your browser on first connect and tokens refresh automatically — there is no client id, secret, scope, or authorization-server URL to configure.

Claude Code

Run the following in your terminal:

claude mcp add --transport http Meticulous https://app.meticulous.ai/api/mcp

Then, in Claude Code, type /mcp and choose "Authenticate" for the Meticulous MCP.

Cursor

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project):

{
  "mcpServers": {
    "Meticulous": { "url": "https://app.meticulous.ai/api/mcp" }
  }
}

Codex/ChatGPT

Add a server with name "Meticulous" and URL https://app.meticulous.ai/api/mcp, then click "Authenticate".

Authenticating with a token instead

Any MCP client can also authenticate with a static bearer token instead of the browser OAuth flow — useful in CI, or wherever an interactive login isn't possible. The token is a Meticulous OAuth token or a project API token (see the setup guide for how to obtain one).

{
  "url": "https://app.meticulous.ai/api/mcp",
  "headers": { "Authorization": "Bearer <token>" }
}

Available tools

Each tool takes broadly the same arguments as the matching agent CLI command and returns the same data as its --json output — with minor differences inherent to a hosted endpoint rather than a local CLI (for example, no git-inferred commitSha and no output-format flags). See the CLI commands page for what each command does and its arguments. Once connected, your client discovers these tools automatically and makes them available to your agent: