Connect an MCP server so the AI can use its tools. See MCP Servers Explained first.
Before you start
The Manage AI Settings right, and the server's MCP endpoint URL (for example https://tools.example.com/mcp). Servers must be reachable over the internet; a server that runs as a program on your own computer (stdio) cannot be added — host it behind Streamable HTTP first.
Steps
- Go to Settings → Artificial Intelligence → MCP Servers.
- Click Add Server.
- Fill in Name and Description.
- Choose a Transport Type: Streamable HTTP (recommended), or Server-Sent Events (legacy) for older servers.
- Enter the Server URL and any headers the server needs, such as
Authorization. Saved header values are hidden; choose Replace to change one. - Turn on Available to AI members if AI members should use this server. They can use only its read-only tools.
- Click Create server, then Test connection (the lightning button on the server's row). A healthy server reports how many tools it has.
What you'll see
The server's tools appear to the AI with the prefix shown in Tool prefix (for example ext_docs_search). Toggle a server off to stop using it without deleting it.
Related articles
Other guides that answer questions close to this one.
MCP Servers Explained
An MCP (Model Context Protocol) server gives the AI access to external tools — a standard way for an AI model to call a tool or data source outside Kamo, instead of every integration needing its own wiring. Two…
How to Add an AI Provider
Connect an AI service your organization pays for, so its models can answer your team and your AI members. Before you start You need the Manage AI Settings permission, and your organization must have the AI Assistant app…
How to Create an AI Access Policy
Set how much the people in one or more roles may use AI each day, and which providers and models they may use. Before you start You need the Manage AI Settings permission. See AI Security Models Explained for what a…