# MCP overview (/docs/mcp)



MCP [#mcp]

MCP (Model Context Protocol) lets AI tools securely read your SageOx knowledge — no scraping, no copies, just your permissions extended.

When you connect, your AI tool gets a scoped OAuth grant that maps to **your** SageOx account. It sees what you see — your personal bubble plus any team, repo, or shared bubbles where you're a member. Nothing more.

Connect your tool [#connect-your-tool]

Connect from the wizard at [`/connect/mcp`](/connect/mcp) — pick your tool and connect in one click. The wizard handles one-click setup for Cursor, VS Code, Windsurf, Goose, Claude Code, Claude Desktop, ChatGPT, and Copilot Studio, and walks you through the OAuth grant.

Using a different client? Point it at the [raw URL and canonical `mcpServers` JSON](/docs/mcp/manual).

What MCP does for you [#what-mcp-does-for-you]

Once connected, your AI tool can:

* **See your teams.** "What teams am I on in SageOx?"
* **Search team knowledge.** "What did we decide about the ingestion retry policy?"
* **Save sessions.** "Save this conversation as a session in the Marketing bubble."
* **Read bubble content.** "What's in the SageOx Marketing bubble?"

The scopes are presented when you authorize — you can see exactly what the tool will be able to do before you click Approve.

Once you're connected, [**Getting the most out of SageOx**](/docs/mcp/getting-the-most) shows how to prompt your tool well and what the interactive cards do.

Managing connections [#managing-connections]

Active MCP grants are listed at [`/settings/security`](/settings/security). You can disconnect individual clients or disconnect all at once. Disconnecting forces the client to reauthorize on its next call — there's no token left behind.