mcp/mongodb repository overview

⁠MongoDB MCP Server

A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.

What is an MCP Server?⁠

⁠MCP Info

⁠Image Building Info

Attribute	Details
Dockerfile	https://github.com/mongodb-js/mongodb-mcp-server/blob/e99ccd0fde6b4c509d88d9941effa4847c2e93e9/Dockerfile⁠
Commit	e99ccd0fde6b4c509d88d9941effa4847c2e93e9
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/mongodb --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	Apache License 2.0

⁠Available Tools (25)

⁠Tools Details

⁠Tool: aggregate

Run an aggregation against a MongoDB collection

⁠Usage Rules for $vectorSearch

• Index Type Detection: Use the collection-indexes tool to determine if the target field has a classic vector index (type: 'vector') or an auto-embed index (type: 'autoEmbed').
• Classic Vector Search (type: 'vector'): Use 'queryVector' with embeddings as an array of numbers.
• Auto-Embed Vector Search (type: 'autoEmbed'): Use 'query' - MongoDB automatically generates embeddings at query time. Do NOT use 'queryVector' or 'embeddingParameters' for auto-embed indexes.
• Unset embeddings: Unless the user explicitly requests the embeddings, add an $unset stage at the end of the pipeline to remove the embedding field and avoid context limits. The $unset stage in this situation is mandatory.
• Pre-filtering: If the user requests additional filtering, include filters in $vectorSearch.filter only for pre-filter fields in the vector index. NEVER include fields in $vectorSearch.filter that are not part of the vector index.
• Post-filtering: For all remaining filters, add a $match stage after $vectorSearch.
• If unsure which fields are filterable, use the collection-indexes tool to determine valid prefilter fields.
• If no requested filters are valid prefilters, omit the filter key from $vectorSearch.

⁠Usage Rules for $search

• Include the index name, unless you know for a fact there's a default index. If unsure, use the collection-indexes tool to determine the index name.
• The $search stage supports multiple operators, such as 'autocomplete', 'text', 'geoWithin', and others. Choose the approprate operator based on the user's query. If unsure of the exact syntax, consult the MongoDB Atlas Search documentation, which can be found here: https://www.mongodb.com/docs/atlas/atlas-search/operators-and-collectors/⁠

responseBytesLimit|number optional|The maximum number of bytes to return in the response. This value is capped by the server's configured maxBytesPerQuery and cannot be exceeded. Note to LLM: If the entire aggregation result is required, use the "export" tool instead of increasing this limit.

This tool is read-only. It does not modify its environment.

⁠Tool: aggregate-db

Run an aggregation against a MongoDB database

This tool is read-only. It does not modify its environment.

⁠Tool: collection-indexes

Describe the indexes for a collection

This tool is read-only. It does not modify its environment.

⁠Tool: collection-schema

Describe the schema for a collection

This tool is read-only. It does not modify its environment.

⁠Tool: collection-storage-size

Gets the size of the collection

This tool is read-only. It does not modify its environment.

⁠Tool: connect

Connect to a MongoDB instance. The config resource captures if the server is already connected to a MongoDB cluster. If the user has configured a connection string or has previously called the connect tool, a connection is already established and there's no need to call this tool unless the user has explicitly requested to switch to a new MongoDB cluster.

This tool is read-only. It does not modify its environment.

⁠Tool: count

Gets the number of documents in a MongoDB collection using db.collection.count() and query as an optional filter parameter

This tool is read-only. It does not modify its environment.

⁠Tool: create-collection

Creates a new collection in a database. If the database doesn't exist, it will be created automatically.

⁠Tool: create-index

Create an index for a collection

⁠Tool: db-stats

Returns statistics that reflect the use state of a single database

This tool is read-only. It does not modify its environment.

⁠Tool: delete-many

Removes all documents that match the filter from a MongoDB collection

This tool may perform destructive updates.

⁠Tool: drop-collection

Removes a collection or view from the database. The method also removes any indexes associated with the dropped collection.

This tool may perform destructive updates.

⁠Tool: drop-database

Removes the specified database, deleting the associated data files

This tool may perform destructive updates.

⁠Tool: drop-index

Drop an index for the provided database and collection.

This tool may perform destructive updates.

⁠Tool: explain

Returns statistics describing the execution of the winning plan chosen by the query optimizer for the evaluated method

This tool is read-only. It does not modify its environment.

⁠Tool: export

Export a query or aggregation results in the specified EJSON format.

This tool is read-only. It does not modify its environment.

⁠Tool: find

Run a find query against a MongoDB collection

This tool is read-only. It does not modify its environment.

⁠Tool: insert-many

Insert an array of documents into a MongoDB collection. If the list of documents is above com.mongodb/maxRequestPayloadBytes, consider inserting them in batches.

⁠Tool: list-collections

List all collections for a given database

This tool is read-only. It does not modify its environment.

⁠Tool: list-databases

List all databases for a MongoDB connection

⁠Tool: list-knowledge-sources

List available data sources in the MongoDB Assistant knowledge base. Use this to explore available data sources or to find search filter parameters to use in search-knowledge.

⁠Tool: mongodb-logs

Returns the most recent logged mongod events

This tool is read-only. It does not modify its environment.

⁠Tool: rename-collection

Renames a collection in a MongoDB database

⁠Tool: search-knowledge

Search for information in the MongoDB Assistant knowledge base. This includes official documentation, curated expert guidance, and other resources provided by MongoDB. Supports filtering by data source and version.

This tool is read-only. It does not modify its environment.

⁠Tool: update-many

Updates all documents that match the specified filter for a collection. If the list of documents is above com.mongodb/maxRequestPayloadBytes, consider updating them in batches.

⁠Use this MCP Server

{
  "mcpServers": {
    "mongodb": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MDB_MCP_CONNECTION_STRING",
        "mcp/mongodb"
      ],
      "env": {
        "MDB_MCP_CONNECTION_STRING": "mongodb+srv://username:[email protected]/myDatabase"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠