Connect Claude to MongoDB

Explore databases, collections, schemas and indexes, then read documents with find, count and aggregate. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Sandboxed MCP server
Authentication: Connection string
Actions exposed: 11
Cost per call (typical): 5 credits
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install MongoDB
Open the marketplace in your workspace, add MongoDB to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with connection string. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. MongoDB shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What MongoDB asks for

Connection string. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Connection stringRequired: An Atlas SRV string or a plain mongodb:// URI. Use a database user with the readAnyDatabase role, or a role scoped to the one database you want reachable - this connector cannot write, but a narrow user also bounds what it can read.; mongodb+srv://user:[email protected]/

What Claude can do in MongoDB

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 11Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_databases
List the databases on this deployment with their size on disk. Call this first - every other action names a database.
list_collections
List the collections in one database. Use it to find the collection name before describing or querying it.
collection_schema
Infer one collection's schema by sampling documents: the field names, their types and how often each appears. MongoDB has no declared schema, so this sample is the closest thing to one - call it before writing a filter against an unfamiliar collection.
collection_indexes
List the indexes on one collection with their keys and options. Check this before assuming a filter or sort will be fast.
collection_storage_size
Report how much disk one collection uses. Use it to find what is filling a deployment.
db_stats
Report one database's statistics: collection count, document count, data size, storage size and index size.
find
Run a find query and return matching documents. The filter, projection and sort are MongoDB query documents, passed through as structured JSON rather than assembled into JavaScript. The server caps how many documents and how many bytes one call can return.
count_documents
Count the documents in a collection matching a query, without returning any of them. Use it to size a result before running find.
aggregate
Run an aggregation pipeline and return the result documents. This is how you group, join with $lookup, or compute totals. A pipeline containing $out or $merge is refused by the server, because those stages write.
explain
Return the query plan for a find, count or aggregate without returning its results. Use it to find out whether a query uses an index before running it over a large collection.
server_logs
Return recent entries from the deployment's own log, or the startup warnings. Use it when a query is failing and you need to tell a server problem from a bad query.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches MongoDB rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in MongoDB.
It reaches no further than your credential: Toolspoke holds no access to MongoDB of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from MongoDB: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in MongoDB. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around MongoDB's own rate limits. A call that MongoDB refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in MongoDB?

11 named actions: 11 that only read. They include list_databases, list_collections and collection_schema. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the MongoDB connector need?

Connection string. The connector asks for connection string. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the MongoDB connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the MongoDB connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches MongoDB rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in MongoDB. Toolspoke holds no access to MongoDB of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in MongoDB. An agent has to ask. Toolspoke does not retry, queue or back off around MongoDB's own rate limits. A call that MongoDB refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches MongoDB's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls MongoDB?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More database connectors

Browse all of them