MCP Server

Give AI coding tools direct access to your Briefs, Tasks, and project context through the Model Context Protocol. The Hamster plugin connects your tool to the hosted server, with no API keys to manage.

Overview

The Hamster MCP Server lets Claude Code, Cursor, Codex, Antigravity, Windsurf, and other MCP clients work with live Hamster context. Full user sessions can search the workspace, inspect accounts and members, read and write Briefs, Tasks, notes, Initiatives, and subtasks, read Goals, documents, Plans, and knowledge-graph relationships, ask Hamster a workspace question, generate Plans, and trigger delivery.

Most people connect through the Hamster plugin, which configures the hosted MCP Server at https://tryhamster.com/mcp in every supported tool with MCP support (Pi uses the CLI instead), and your AI coding tool handles the OAuth sign-in. Subsequent calls are automatic.

Its tools cover search, accounts, members, Briefs, Tasks, subtasks, Initiatives, Goals, documents, Plans, Delivery, notes, chat, and the Context Graph. All access goes through your authenticated session and respects the same permissions you have in the browser. There are no admin keys involved — every call runs as you, scoped to your team's data.

Hosted delivery receives a separate, smaller set of tools bound to one delivery job and one delivery resource — a Brief or Task. Most full-scope tools have a CLI counterpart; Available Tools lists every tool in both scopes and the few that are MCP-only. Every call follows the account permissions or job-and-resource scope of its credential.

What's in this section

How Authentication Works

Hamster's MCP Server uses OAuth 2.1. When your AI coding tool signs in:

  1. The tool sees that it needs to authenticate and looks up Hamster's OAuth configuration via a discovery endpoint at /.well-known/oauth-protected-resource. This is a public, machine-readable record that tells the tool where to send you for sign-in.
  2. The tool opens your browser to Hamster's consent page.
  3. You sign in (or confirm if you are already signed in) and approve the connection.
  4. The browser returns an authorization code to your AI tool, which exchanges it (with a PKCE verifier) for tokens.
  5. Every subsequent call runs as you, with your team-account permissions enforced server-side.

Most AI coding tools handle this flow for you, and you usually see the browser only on first sign-in. If your tool does not support automatic OAuth discovery, you can still paste a Bearer token manually.

Where sign-in starts depends on the tool; the Install section of Hamster plugin lists each one.

The MCP Server never holds an admin key or service-role credential. Every tool call carries your token, which means a Reviewer cannot accidentally edit a Brief from inside their AI assistant just because the assistant tried to.