Skip to main content
The data, actions, and workflows you’ve built aren’t just for the Forest UI. Forest ships an MCP server that exposes the same capabilities to AI agents like Claude, enforcing the exact same permissions and writing the same audit trail, regardless of whether a human or an AI agent is acting. An AI agent request hits the /mcp endpoint, passes the same permissions and role check as a human (allowed or blocked), reaches the Forest back-end, and is written to the audit log

​
What the MCP server exposes

Through the Model Context Protocol, connected AI agents can:
  • Browse your collections and their schemas
  • Query and filter records across collections
  • Execute actions on records, including approval workflows
  • Start workflows on a record and follow their progress
Every operation on data runs with the permissions of the authenticated Forest user, and is logged just like a UI action — with four exceptions, listed under Identity, auditing, and limits. The three workflow tools are the exception to the permission half: discovering, triggering and reading runs are gated by the user’s rendering and the workflow’s MCP toggle only — no collection permission, no segment, and no check on the target record. What the run then reads and writes is bound by that user’s permissions as usual.

​
Turn on the MCP server

With the Node.js back-end, enable the Forest Gateway’s MCP service when you create the back-end in your index.js:
addGateway() ships with @forestadmin/agent 1.109.0. MCP alone installs nothing extra: @forestadmin/agent-bff is only loaded when the API service is enabled too. addGateway() is called once per agent, so this call is the one to extend later, not one to repeat. Restart your back-end. You should see:
Your MCP endpoint is now available at <your-back-end-url>/mcp.
You can find your back-end URL in Project Settings → Environments. Each environment has its own back-end URL, and therefore its own MCP endpoint.

​
Restrict which tools are exposed

By default all tools are enabled. To expose only a subset, pass enabledTools, new tools added in future releases stay off until you opt in. This replaces the addGateway({ mcp: true }) call above rather than adding to it, one call per agent:
describeCollection is always enabled, it’s required for the server to function.

​
Connect Claude

Point your AI assistant at the MCP endpoint. On first connection, a browser window opens for you to log in with your Forest credentials, the assistant then operates with that user’s permissions.
Use the transport type http (the Forest MCP server uses Streamable HTTP). For other clients (Claude Desktop, Cursor, VS Code, Codex) and the standalone deployment option, see the Forest MCP Server reference.
Only grant MCP access to trusted AI tools and users. The server can perform any operation the authenticated user can perform.

​
What’s next

Your operations are now available to your team and your AI agents. Time to move everything to production.

Next: Deploy →

Deploy your Forest back-end to production