MongoDB Mongoose MCP
An MCP server for MongoDB with optional Mongoose schema support.
MongoDB Mongoose MCP
An MCP (Model Context Protocol) server that enables Claude to interact with MongoDB databases, with optional Mongoose schema support.
Features
- Query, aggregation, insert, update, and manage MongoDB collections directly from Claude
- Optional Mongoose schema support for data validation and hooks
- Soft delete implementation for document safety
- Clean separation between schema-based and schemaless operations
Prerequisites
- Node.js (v18 or higher)
- MongoDB
Integrating with Claude Desktop
To add the MCP server to Claude Desktop:
- Go to Settings > Developer > Edit config
- Add the following to your claude_desktop_config.json file:
{
"mcpServers": {
"mongodb-mongoose": {
"command": "npx",
"args": [
"-y",
"mongo-mongoose-mcp",
],
"env": {
"MONGODB_URI": "<your mongodb uri>",
"SCHEMA_PATH" : "<path to the root folder of all your mongoose schema objects>"
}
}
}
}
Available MCP Commands
When integrated with Claude, the following commands become available:
Query Tools
find: Query documents with filtering and projectionlistCollections: List available collectionsinsertOne: Insert a single documentupdateOne: Update a single documentdeleteOne: Soft delete a single documentcount: Count documents with filteringaggregate: Query documents with aggregation pipeline
Index Tools
createIndex: Create a new indexdropIndex: Remove an indexindexes: List indexes for a collection
Example Usage
Once integrated with Claude Desktop, you can use natural language to interact with your MongoDB database:
- "Show me all users in my database who are older than 30"
- "Insert a new product with name 'Widget X', price $29.99, and category 'Electronics'"
- "Count all completed orders from the past week"
- "Create an index on the email field of the users collection"
For Developers
Building from Source
# Clone the repository
git clone https://github.com/nabid-pf/mongo-mongoose-mcp.git
cd mongo-mongoose-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Test with the MCP inspector
npx @modelcontextprotocol/inspector node dist/index.js
Creating Mongoose Schemas
Place your Mongoose schema object files in the a directory and specify that path in SCHEMA_PATH var Make sure file names reflect the collection name
// models/users.js (for users collection)
export default {
name: { type: String, required: true },
email: { type: String, required: true, unique: true },
age: Number,
createdAt: { type: Date, default: Date.now },
isDeleted: { type: Boolean, default: false },
deletedAt: Date
};
How It Works
This project uses:
- MongoDB native driver for direct database operations
- Mongoose for schema-based operations when schemas are available
- The Model Context Protocol (MCP) to communicate with Claude
License
MIT
Máy chủ liên quan
Memory
Knowledge graph-based persistent memory system
ParticlePhysics MCP Server
Provides seamless access to particle physics data from the Particle Data Group (PDG) for AI assistants and applications.
MongoDB
Interact with MongoDB databases using natural language to query collections, inspect schemas, and manage data.
Redis MCP Server
A natural language interface for agentic applications to manage and search data in Redis.
QuickBooks Online by CData
A read-only MCP server for querying live QuickBooks Online data. Requires a separate CData JDBC Driver for QuickBooks Online.
MCP Knowledge Graph
Provides persistent memory for AI models using a local knowledge graph.
Neon MCP Server
Interact with Neon Postgres databases using natural language to manage projects, branches, queries, and migrations via the Neon API.
MCP ODBC Server
Access ODBC-accessible data sources using a configured Data Source Name (DSN).
Kintone Lite
A lightweight server to connect AI assistants with Kintone applications and data.
Prometheus
Retrieve and analyze time-series data from Prometheus databases using PromQL queries.
