MCP (Model Context Protocol) lets you connect external tool servers to Devin for Terminal, giving the agent access to APIs, databases, issue trackers, and any other service you can wrap in an MCP server. When you configure an MCP server, its tools become available to the agent just like built-in tools. The agent can discover what tools are available and call them as needed.Documentation Index
Fetch the complete documentation index at: https://cli.devin.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
How It Works
Configure a server
You define an MCP server in your config file with a command, arguments, and optional environment variables.
Server launches
Devin for Terminal starts the server process when needed. The server connects to the external API (GitHub, Linear, etc.).
Quick Example
Add a GitHub MCP server to your project:Permission Control
Once configured, MCP tools appear with a namespaced format:mcp__<server>__<tool>. For example, a “github” server with a “create_issue” tool becomes mcp__github__create_issue.
MCP tools are subject to the same permission system as built-in tools. You can control access at multiple levels:
Authentication
Some remote MCP servers (such as Atlassian, Notion, and Linear) require OAuth authentication. Each MCP client authenticates independently — tokens from Windsurf or Claude Code are not shared with Devin for Terminal. After adding a remote server, authenticate with:Next Steps
Configuration
Learn how to configure MCP servers in detail
Permissions
Control which MCP tools the agent can use

