Give an AI assistant access to your data
Connect Claude, Cursor or any MCP client to your databases, and decide what it may reach and what it has to ask for first.
Monghoul runs a Model Context Protocol server with 70+ tools, so an assistant queries your databases through the connection profiles you already have. The server is loopback only and authenticated with a token.
The interesting part is not the tools. It is deciding what an assistant can reach.
The three-step setup
A new setup starts with nothing selected, which is the right default and means you cannot enable this by accident.
- Pick the connections and tools the assistant may reach.
- Copy its configuration. There are ready-made snippets for the common clients.
- Start access.
Decide the scope before the permissions
Access is either unrestricted or limited to selected connections and databases. Anything outside the scope is hidden from discovery, and an action that targets it is refused rather than failing oddly.
One behaviour worth knowing: connection-wide access includes databases discovered later. Database-specific access does not. If you grant a whole connection today, a database created next month is in scope.
This organises what the assistant reaches. It does not replace MongoDB permissions. For a real boundary, connect with a MongoDB user that only has the roles you want.
Then the permissions
Permissions are one row per kind of change, each set to Ask first or Allow:
| Kind | Default |
|---|---|
| Looking at things | Reads always run |
| Changing the workspace | Allowed |
| Deleting things inside Monghoul | Ask first |
| Anything touching a database | Ask first |
Any single tool can be overridden to always ask or never ask, whatever its row says.
What an approval looks like
It names the operation, what it lands on, and any destructive methods found in submitted code. It declines itself after ten minutes if you ignore it, so a forgotten prompt does not sit open.
A non-destructive tool can be approved for the rest of the session. That grant ends with the assistant and is never written to disk.
Afterwards
There is an activity record of every call the assistant made, kept locally. Read it the first week. It is the fastest way to find out whether the scope you chose was the scope you meant.
Next
- AI access reference
- Write protection, which applies to assistants too