# io.github.mongodb-js/mongodb-mcp-server (oci · docker.io/mongodb/mongodb-mcp-server:2.1.0)

MongoDB Model Context Protocol Server

- Trust score: 52/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `mongodb-mcp-server`: 49/100, [markdown](https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/mongodb-mcp-server.md), [page](https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/mongodb-mcp-server)
- oci · `docker.io/mongodb/mongodb-mcp-server:2.1.0`: 52/100 (this document), [markdown](https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0.md), [page](https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0)

## Channel facts

- Registry: `oci`
- Package: `docker.io/mongodb/mongodb-mcp-server:2.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 17 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3973 tokens (~137/item across 29 items; 27 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (89% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.mongodb-js/mongodb-mcp-server server?

io.github.mongodb-js/mongodb-mcp-server runs locally as a container image, launched with docker run --rm -i docker.io/mongodb/mongodb-mcp-server:2.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mongodb-js-mongodb-mcp-server -- docker run --rm -i docker.io/mongodb/mongodb-mcp-server:2.1.0
```

### Cursor

```json
{
  "mcpServers": {
    "mongodb-js-mongodb-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/mongodb/mongodb-mcp-server:2.1.0"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mongodb-js-mongodb-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/mongodb/mongodb-mcp-server:2.1.0"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mongodb-js-mongodb-mcp-server -- docker run --rm -i docker.io/mongodb/mongodb-mcp-server:2.1.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mongodb-js-mongodb-mcp-server": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "docker.io/mongodb/mongodb-mcp-server:2.1.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  mongodb-js-mongodb-mcp-server:
    command: "docker"
    args: ["run", "--rm", "-i", "docker.io/mongodb/mongodb-mcp-server:2.1.0"]
```

### Netclaw

```json
{
  "McpServers": {
    "mongodb-js-mongodb-mcp-server": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "docker.io/mongodb/mongodb-mcp-server:2.1.0"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "mongodb-js-mongodb-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/mongodb/mongodb-mcp-server:2.1.0"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 50, −3)

- [functional] Stability: pass → 0.80

### 2026-09-16 (score 53, 0)

- [security] Stability: 0.97 → pass

### 2026-09-15 (score 53, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 50, −3)

- [functional] Stability: pass → 0.80

## MCP tools (27)

### `aggregate-db` (~154 tokens)

Run an aggregation against a MongoDB database

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `pipeline` (array, required): An array of aggregation stages to execute. The first stage must be a database-level aggregation stage (one of `$changeStream`, `$currentOp`, `$documents`, `$listLocalSessions`, `$queryStats`). https:…
- `responseBytesLimit` (number): The maximum number of bytes to return in the response. This value is capped by the server's configured maximum and cannot be exceeded.

Output parameters:

- `aggResultsCount` (number): The total number of documents returned by the aggregation pipeline
- `appliedLimits` (array): The limits applied to the aggregation pipeline
- `documents` (array): The documents returned by the aggregation pipeline

### `aggregate` (~1365 tokens)

Run an aggregation against a MongoDB collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `pipeline` (array, required): An array of aggregation stages to execute. If the user has asked for a vector search, `$vectorSearch` **MUST** be the first stage of the pipeline (or the first stage of a `$unionWith` sub-pipeline o…
- `responseBytesLimit` (number): The maximum number of bytes to return in the response. This value is capped by the server's configured maximum and cannot be exceeded.

Output parameters:

- `appliedLimits` (array): The limits applied to the aggregation pipeline
- `count`: The total number of documents returned by the aggregation pipeline
- `documents` (array): The documents returned by the aggregation pipeline

### `collection-indexes` (~60 tokens)

Describe the indexes for a collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `classicIndexes` (array)
- `classicIndexesCount` (number)
- `searchIndexes` (array)
- `searchIndexesCount` (number)

### `collection-schema` (~109 tokens)

Describe the schema for a collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `responseBytesLimit` (number): The maximum number of bytes to return in the response. This value is capped by the server's configured maximum and cannot be exceeded.
- `sampleSize` (number): Number of documents to sample for schema inference

Output parameters:

- `fieldsCount` (number)
- `schema` (object)

### `collection-storage-size` (~60 tokens)

Gets the size of the collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `size` (number)
- `units` (string)

### `connect` (~118 tokens)

Connect to a MongoDB instance and get back a connectionId to pass to the other MongoDB tools. Each call establishes a new, independent connection — multiple connections can be active at the same time.

Input parameters:

- `connectionName` (string): Optional short label for the connection (stored slugified with a short suffix, e.g. "staging" becomes staging-<suffix>). Shown in connection listings; helpful for telling multiple connections apart.
- `connectionString` (string, required): MongoDB connection string (in the mongodb:// or mongodb+srv:// format)

Output parameters:

- `connectionId` (string)

### `count` (~106 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `query` (object): A filter/query parameter. Allows users to filter the documents to count. Matches the syntax of the filter argument of db.collection.count().

Output parameters:

- `count` (number): The number of documents in the collection

### `create-collection` (~73 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `collection` (string)
- `created` (boolean)
- `database` (string)

### `create-index` (~111 tokens)

Create an index for a collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `definition` (array, required): The index definition. Use 'classic' for standard indexes, 'vectorSearch' for vector search indexes, and 'search' for Atlas Search (lexical) indexes.
- `name` (string): The name of the index

Output parameters:

- `collection` (string)
- `database` (string)
- `indexName` (string)
- `indexType` (string)

### `db-stats` (~56 tokens)

Returns statistics that reflect the use state of a single database

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `stats` (object)

### `delete-many` (~93 tokens)

Removes all documents that match the filter from a MongoDB collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `filter` (object): The query filter, specifying the deletion criteria. Matches the syntax of the filter argument of db.collection.deleteMany()

Output parameters:

- `collection` (string)
- `database` (string)
- `deletedCount` (number)

### `disconnect` (~44 tokens)

Close a MongoDB connection and revoke its connectionId.

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.

Output parameters:

- `outcome` (string)

### `drop-collection` (~74 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `collection` (string)
- `database` (string)
- `dropped` (boolean)

### `drop-database` (~55 tokens)

Removes the specified database, deleting the associated data files

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `database` (string)
- `dropped` (boolean)

### `drop-index` (~111 tokens)

Drop an index for the provided database and collection.

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `indexName` (string, required): The name of the index to be dropped.
- `type` (string, required): The type of index to be deleted. Use 'classic' for standard indexes and 'search' for atlas search and vector search indexes.

Output parameters:

- `collection` (string)
- `database` (string)
- `dropped` (boolean)
- `indexName` (string)

### `explain` (~135 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `method` (array, required): The method and its arguments to run
- `verbosity` (string): The verbosity of the explain plan, defaults to queryPlanner. If the user wants to know how fast is a query in execution time, use executionStats. It supports all verbosities as defined in the MongoDB…

Output parameters:

- `explainResult` (object)
- `method` (string)
- `verbosity` (string)

### `export` (~188 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `exportTarget` (array, required): The export target along with its arguments.
- `exportTitle` (string, required): A short description to uniquely identify the export.
- `jsonExportFormat` (string): The format to be used when exporting collection data as EJSON with default being relaxed. relaxed: A string format that emphasizes readability and interoperability at the expense of type preservation…

### `find` (~206 tokens)

Run a find query against a MongoDB collection

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `filter` (object): The query filter, matching the syntax of the query argument of db.collection.find()
- `limit` (number): The maximum number of documents to return
- `projection` (object): The projection, matching the syntax of the projection argument of db.collection.find()
- `responseBytesLimit` (number): The maximum number of bytes to return in the response. This value is capped by the server's configured maximum and cannot be exceeded.
- `sort` (object): A document, describing the sort order, matching the syntax of the sort argument of cursor.sort(). The keys of the object are the fields to sort on, while the values are the sort directions (1 for asc…

Output parameters:

- `appliedLimits` (array): The limits applied to the find query
- `documents` (array): The documents returned by the find query
- `queryResultsCount` (number): The total number of documents returned by the find query

### `insert-many` (~109 tokens)

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

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `documents` (array, required): The array of documents to insert, matching the syntax of the document argument of db.collection.insertMany().

Output parameters:

- `collection` (string)
- `database` (string)
- `insertedCount` (number)
- `insertedIds` (array)

### `list-collections` (~52 tokens)

List all collections for a given database

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name

Output parameters:

- `collections` (array)
- `totalCount` (number)

### `list-connections` (~30 tokens)

List the active MongoDB connections and their connectionIds. Use this to find a connectionId established earlier.

Output parameters:

- `connections` (array)

### `list-databases` (~45 tokens)

List all databases for a MongoDB connection

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.

Output parameters:

- `databases` (array)
- `totalCount` (number)

### `mongodb-logs` (~93 tokens)

Returns the most recent logged mongod events

Input parameters:

- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `limit` (integer): The maximum number of log entries to return.
- `type` (string): The type of logs to return. Global returns all recent log entries, while startupWarnings returns only warnings and errors from when the process started.

Output parameters:

- `logs` (array)
- `shownCount` (number)
- `totalLinesWritten` (number)

### `rename-collection` (~95 tokens)

Renames a collection in a MongoDB database

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `dropTarget` (boolean): If true, drops the target collection if it exists
- `newName` (string, required): The new name for the collection

Output parameters:

- `database` (string)
- `newCollection` (string)
- `oldCollection` (string)
- `renamed` (boolean)

### `update-many` (~150 tokens)

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.

Input parameters:

- `collection` (string, required): Collection name
- `connectionId` (string, required): The connection to run the operation against. Use the id returned by one of the connect tools.
- `database` (string, required): Database name
- `filter` (object): The selection criteria for the update, matching the syntax of the filter argument of db.collection.updateOne()
- `update` (object, required): An update document describing the modifications to apply using update operator expressions
- `upsert` (boolean): Controls whether to insert a new document if no documents match the filter

Output parameters:

- `collection` (string)
- `database` (string)
- `matchedCount` (number)
- `modifiedCount` (number)
- `upsertedCount` (number)
- `upsertedId` (string)

### `list-knowledge-sources` (~43 tokens)

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.

### `search-knowledge` (~171 tokens)

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.

Input parameters:

- `dataSources` (array): A list of one or more data sources to limit the search to. You can specify a specific version of a data source by providing the version label. If not provided, the latest version of all data sources…
- `limit` (number): The maximum number of results to return
- `query` (string, required): A natural language query to search for in the MongoDB Assistant knowledge base. This should be a single question or a topic that is relevant to the user's MongoDB use case.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0#diagnostics

## Score history

- 2026-09-20: 52
- 2026-09-19: 51
- 2026-09-18: 51
- 2026-09-17: 50
- 2026-09-16: 53
- 2026-09-15: 53
- 2026-09-14: 52
- 2026-09-13: 52
- 2026-09-12: 51
- 2026-09-11: 51
- 2026-09-10: 50
- 2026-09-09: 53
- 2026-09-08: 53
- 2026-09-07: 52
- 2026-09-06: 52
- 2026-09-05: 51
- 2026-09-04: 51
- 2026-09-03: 50
- 2026-09-02: 50
- 2026-09-01: 49
- 2026-08-31: 49
- 2026-08-30: 49
- 2026-08-29: 48
- 2026-08-28: 48
- 2026-08-27: 47
- 2026-08-26: 47
- 2026-08-25: 45
- 2026-08-24: 45
- 2026-08-23: 44
- 2026-08-22: 44

## Common questions

### What is the io.github.mongodb-js/mongodb-mcp-server server?

io.github.mongodb-js/mongodb-mcp-server is listed in the public MCP registry as io.github.mongodb-js/mongodb-mcp-server. MongoDB Model Context Protocol Server. This page covers its container image (docker.io/mongodb/mongodb-mcp-server:2.1.0).

### Is the io.github.mongodb-js/mongodb-mcp-server server safe to use?

io.github.mongodb-js/mongodb-mcp-server scores 52 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.mongodb-js/mongodb-mcp-server server expose?

io.github.mongodb-js/mongodb-mcp-server exposes 27 tools: aggregate-db, aggregate, collection-indexes, collection-schema, collection-storage-size, and 22 more. Their descriptions and schemas cost roughly 3,906 tokens of context every time the server is loaded.

### Is the io.github.mongodb-js/mongodb-mcp-server server still maintained?

io.github.mongodb-js/mongodb-mcp-server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Repository: https://github.com/mongodb-js/mongodb-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0.xml
- Changelog JSON feed: https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0.json
- HTML version of this page: https://verifymcp.io/servers/mongodb-js-mongodb-mcp-server/docker-io-mongodb-mongodb-mcp-server-2-1-0