If your team has its own internal tools or data sources — something not covered by the standard connections — you can plug it in as a custom MCP server.
MCP (Model Context Protocol) is an open standard for safely exposing a tool or data source to an AI coworker. Think of it as a well-defined, secure doorway between your systems and your coworkers.
How it works
Add the server address
In the console, enter the address of your MCP-compatible server.
The console verifies it
A quick check confirms the connection is reachable and correctly configured.
Your coworkers can use it
Once verified, any coworker on your team can draw on it when relevant.
Connection status
| Status | What it means |
|---|
| Verified | Connected and working |
| Not tested yet | Added, but not yet checked |
| Authentication failed | The server rejected the credentials — check them and try again |
| Unreachable | The console couldn’t reach the address — check the server is running and accessible |
Setting up a custom MCP server usually involves someone from your engineering or IT team. If that’s not you, see Connections Hub for the ready-made options instead. 