MongoDB Mongoose MCP Server

What does “MongoDB Mongoose” MCP Server do?

The MongoDB Mongoose MCP Server is a Model Context Protocol (MCP) server that enables AI assistants, such as Claude, to interact directly with MongoDB databases. With optional Mongoose schema support, it allows for robust data validation and operational hooks. This server empowers AI-driven workflows to perform a wide range of database tasks, including querying, aggregation, insertion, updating, and management of MongoDB collections. Its design supports both schema-based and schemaless operations, providing flexibility for diverse development environments. By exposing database actions as tools, MongoDB Mongoose MCP enhances developer productivity, streamlines data management, and enables secure, natural language-driven access to critical data infrastructure.

List of Prompts

No explicit prompt templates are listed in the repository documentation or files.

List of Resources

No explicit MCP resources are detailed in the documentation or repository files.

Query Tools

• find: Query documents with filtering and projection.
• listCollections: List all available collections in the database.
• insertOne: Insert a single document into a collection.
• updateOne: Update a single document within a collection.
• deleteOne: Soft delete a single document (marks as deleted without removing).
• count: Count documents matching a filter.
• aggregate: Perform aggregation queries using pipelines.

Index Tools

• createIndex: Create a new index on a collection.
• dropIndex: Remove an index from a collection.
• indexes: List all indexes for a specific collection.

Use Cases of this MCP Server

• Database Management: Enables AI clients to perform CRUD operations, manage indexes, and query data securely via natural language, reducing the need for manual database access.
• Data Exploration: Allows developers to explore and analyze MongoDB collections, run aggregation pipelines, and generate insights interactively.
• Schema Enforcement: With Mongoose integration, developers can enforce data validation and leverage hooks for cleaner data management.
• Soft Deletion Workflows: Supports soft deletion patterns, ensuring that data is not lost but marked for deletion and can be recovered if needed.
• Rapid Prototyping: Facilitates quick testing of database schema changes and data models directly from the AI assistant without manual scripting.

How to set it up

Windsurf

1. Ensure Node.js (v18+) and MongoDB are installed.
2. Locate and edit your Windsurf configuration file.
3. Add the MongoDB Mongoose MCP server to the mcpServers section:

   {
     "mcpServers": {
       "mongodb-mongoose": {
         "command": "npx",
         "args": [
           "-y",
           "mongo-mongoose-mcp"
         ],
         "env": {
           "MONGODB_URI": "<your mongodb uri>",
           "SCHEMA_PATH": "<path to the root folder of your mongoose schema objects>"
         }
       }
     }
   }
   

4. Save the file and restart Windsurf.
5. Verify the MCP server is running and accessible.

Claude

1. Open Claude Desktop Settings > Developer > Edit config.
2. Add the MongoDB Mongoose MCP server in your claude_desktop_config.json:

   {
     "mcpServers": {
       "mongodb-mongoose": {
         "command": "npx",
         "args": [
           "-y",
           "mongo-mongoose-mcp"
         ],
         "env": {
           "MONGODB_URI": "<your mongodb uri>",
           "SCHEMA_PATH": "<path to the root folder of your mongoose schema objects>"
         }
       }
     }
   }
   

3. Save the configuration and restart Claude Desktop.
4. Confirm integration by issuing a database command.

Cursor

1. Install Node.js (v18+) and MongoDB.
2. Open Cursor’s configuration interface.
3. Insert the following JSON under MCP Servers:

   {
     "mcpServers": {
       "mongodb-mongoose": {
         "command": "npx",
         "args": [
           "-y",
           "mongo-mongoose-mcp"
         ],
         "env": {
           "MONGODB_URI": "<your mongodb uri>",
           "SCHEMA_PATH": "<path to mongoose schemas>"
         }
       }
     }
   }
   

4. Save and reload Cursor.
5. Test by running a database query through Cursor.

Cline

1. Ensure prerequisites: Node.js (v18+) and MongoDB.
2. Edit your Cline configuration file.
3. Add:

   {
     "mcpServers": {
       "mongodb-mongoose": {
         "command": "npx",
         "args": [
           "-y",
           "mongo-mongoose-mcp"
         ],
         "env": {
           "MONGODB_URI": "<your mongodb uri>",
           "SCHEMA_PATH": "<path to mongoose schemas>"
         }
       }
     }
   }
   

4. Save the file and restart Cline.
5. Confirm the server is functioning by issuing a supported command.

Securing API Keys

Always store sensitive data such as MONGODB_URI in environment variables. Example configuration:

{
  "mcpServers": {
    "mongodb-mongoose": {
      "command": "npx",
      "args": [
        "-y",
        "mongo-mongoose-mcp"
      ],
      "env": {
        "MONGODB_URI": "${MONGODB_URI}",
        "SCHEMA_PATH": "${SCHEMA_PATH}"
      },
      "inputs": {
        "MONGODB_URI": "set in environment",
        "SCHEMA_PATH": "set in environment"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mongodb-mongoose": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mongodb-mongoose” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: ⛔ (No mention in docs/repo)

Between the two tables, this MCP server implementation is solid for database tools and setup documentation, but lacks information on prompts, explicit resources, roots, and sampling support. It is functionally strong but not fully featured for more advanced MCP concepts.

Our opinion

MCP Score: 6/10
The MongoDB Mongoose MCP is well-documented for setup and tool usage, making it practical for developers focused on database operations. However, the absence of prompt templates, explicit resources, roots, and sampling features limits its completeness for advanced MCP workflows.

MCP Score