MCP, the Model Context Protocol, is an open standard for giving AI agents access to tools and data. With it, a coding agent can work in GitHub, Linear, your docs and more, with access you control. Each coding tool keeps its own MCP setup, including the ones Friday runs.
What is MCP?
MCP is an open standard, introduced by Anthropic, for connecting AI applications to tools and data. Instead of a custom integration for every pairing, a tool offers an MCP server and any agent that speaks MCP can use it.
Why does it matter for coding agents?
- Agents can do things, not just answer questions.
- One MCP server can serve every agent that speaks MCP, so you set a tool up once.
- Access is set in the tool that uses it, so you can keep it narrow.
How do you keep access safe?
- Connect only what the work needs.
- Prefer read-only access where you can.
- Give each agent only the connections it needs.
- Review the tool calls an agent makes.
A tool call that changes data finishes once it starts, so check what an agent is allowed to call before you start it.
What should you connect first?
- Your code host, such as GitHub or GitLab.
- Your issue tracker, such as Linear.
- Your chat, such as Slack.
- Your docs, such as Notion or Google Drive.
How does Friday use MCP?
Friday is a free, MIT-licensed desktop app that runs your coding tools on your own computer, and each tool uses its own MCP setup. Set up an MCP server in Claude Code, Codex, Cursor or another tool the way that tool documents.
Sources
Checked against the MCP documentation and specification on 13 October 2026.
- Introducing the Model Context Protocol, Anthropic
- What is the Model Context Protocol?, MCP docs
- Tools, MCP specification
- Connect Claude Code to tools via MCP, Claude Code docs