Is this an official MongoDB MCP server?

No. It is Memtro's MCP server with Memtro's MongoDB connector behind it: the connector reads MongoDB through its API with the credentials you connect on Dashboard → Connections, and MongoDB publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in MongoDB?

Not yet. Today every MongoDB tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Databases and warehouses

MongoDB MCP server

MongoDB in any MCP client, through Memtro: MongoDB does not publish this server. Memtro's MongoDB connector reads MongoDB through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Read-only access to a MongoDB database or Atlas cluster: sampled collection schemas, find, aggregate, count and distinct with JSON filters, row caps and a 20s time limit. Writes, $out/$merge and server-side JavaScript are refused; use a read-only user anyway.

Reads

mongodb_schemaList databases, or the collections of one database with document counts and a sampled schema (field paths with their BSON types…
mongodb_findFind documents in a collection with a MongoDB query filter (JSON or Extended JSON:…
mongodb_aggregateRun a read-only aggregation pipeline (JSON array of stages, e.g. [{"$match":{…}},{"$group":{"_id":"$status","n":{"$sum":1}}},{"$sort":{"n":-1}}]).
mongodb_countCount documents in a collection matching a filter (exact), or the whole collection (fast estimate when no filter is given).
mongodb_distinctDistinct values of one field (dot paths allowed, e.g. address.country) across a collection, optionally within a filter.

Connect it

First connect MongoDB on Dashboard → Connections, then add Memtro to your client once. The MongoDB tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared MongoDB connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› What collections are in the orders database and what fields do they have?
› How many users signed up last month, by plan?
› Show the 10 most recent failed payments with their error field
› What distinct statuses exist on the shipments collection?
› Which customers have more than 5 open tickets?

Questions

Is this an official MongoDB MCP server?: No. It is Memtro's MCP server with Memtro's MongoDB connector behind it: the connector reads MongoDB through its API with the credentials you connect on Dashboard → Connections, and MongoDB publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in MongoDB?: Not yet. Today every MongoDB tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.