MongoDB MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| aggregateA | Run an aggregation against a MongoDB collection |
| collection-indexesB | Describe the indexes for a collection |
| collection-schemaB | Describe the schema for a collection |
| collection-storage-sizeB | Gets the size of the collection |
| connectA | 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. |
| countA | Gets the number of documents in a MongoDB collection using db.collection.count() and query as an optional filter parameter |
| create-collectionA | Creates a new collection in a database. If the database doesn't exist, it will be created automatically. |
| create-indexB | Create an index for a collection |
| db-statsB | Returns statistics that reflect the use state of a single database |
| delete-manyA | Removes all documents that match the filter from a MongoDB collection |
| drop-collectionA | Removes a collection or view from the database. The method also removes any indexes associated with the dropped collection. |
| drop-databaseA | Removes the specified database, deleting the associated data files |
| drop-indexB | Drop an index for the provided database and collection. |
| explainB | Returns statistics describing the execution of the winning plan chosen by the query optimizer for the evaluated method |
| exportA | Export a query or aggregation results in the specified EJSON format. |
| findB | Run a find query against a MongoDB collection |
| insert-manyB | Insert an array of documents into a MongoDB collection |
| list-collectionsB | List all collections for a given database |
| list-databasesB | List all databases for a MongoDB connection |
| mongodb-logsB | Returns the most recent logged mongod events |
| rename-collectionB | Renames a collection in a MongoDB database |
| update-manyB | Updates all documents that match the specified filter for a collection |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| config | Server configuration, supplied by the user either as environment variables or as startup arguments |
| debug-mongodb | Debugging information for MongoDB connectivity issues. Tracks the last connectivity attempt and error information. |
TDQS
Scored across 22 tools
Each tool has a distinct purpose with clear boundaries, targeting specific MongoDB operations like querying (find, aggregate), management (create-collection, drop-collection), or diagnostics (explain, db-stats). No tools appear to overlap in functionality, making it easy for an agent to select the correct one based on the task.
Most tools follow a consistent verb-noun or noun-verb pattern using kebab-case (e.g., create-collection, list-databases), with a few minor deviations like 'connect' (verb-only) and 'mongodb-logs' (noun-noun). Overall, the naming is predictable and readable, though not perfectly uniform.
With 22 tools, the count is slightly high but reasonable for a comprehensive MongoDB server covering operations from CRUD to administration and diagnostics. It avoids being excessive (under 25) and provides broad coverage without feeling overly bloated for the domain.
The tool set offers complete coverage of MongoDB operations, including CRUD (find, insert-many, update-many, delete-many), schema management (collection-schema, create-index), database/collection lifecycle (create/drop/rename), and diagnostics (explain, logs). No obvious gaps exist for core workflows in this domain.