Labsco
sourabhfb logo

MongoDB That Works

from sourabhfb

A MongoDB MCP server with schema discovery and field validation. Requires a MONGODB_URI environment variable.

🔥🔥🔥✓ VerifiedFreeQuick setup
#email#automation#analytics#database#finance

MongoDB That Works - MCP Server

A reliable MongoDB MCP (Model Context Protocol) server that provides seamless MongoDB integration for Claude Desktop with built-in schema discovery and field validation.

Features

  • 🔍 Schema Discovery: Automatically analyze collection structures
  • ✅ Field Validation: Prevent field name mistakes
  • 📊 Full MongoDB Support: Find, aggregate, insert, update, delete operations
  • 🚀 High Performance: Efficient connection pooling and query optimization
  • 🔐 Secure: Support for MongoDB Atlas and authentication
  • 🎯 Type-Safe: Built with TypeScript and Zod validation

Available Tools

1. listCollections

List all collections in the database.

// Example
mcp.listCollections({ filter: {} })

2. find

Find documents in a collection with filtering, sorting, and pagination.

// Example
mcp.find({
  collection: "users",
  filter: { status: "active" },
  sort: { createdAt: -1 },
  limit: 10
})

3. findOne

Find a single document.

// Example
mcp.findOne({
  collection: "users",
  filter: { email: "user@example.com" }
})

4. aggregate

Run aggregation pipelines.

// Example
mcp.aggregate({
  collection: "orders",
  pipeline: [
    { $match: { status: "completed" } },
    { $group: { _id: "$userId", total: { $sum: "$amount" } } }
  ]
})

5. count

Count documents matching a filter.

// Example
mcp.count({
  collection: "products",
  filter: { inStock: true }
})

6. distinct

Get distinct values for a field.

// Example
mcp.distinct({
  collection: "orders",
  field: "status"
})

7. insertOne

Insert a single document.

// Example
mcp.insertOne({
  collection: "users",
  document: { name: "John Doe", email: "john@example.com" }
})

8. updateOne

Update a single document.

// Example
mcp.updateOne({
  collection: "users",
  filter: { _id: "123" },
  update: { $set: { status: "active" } }
})

9. deleteOne

Delete a single document.

// Example
mcp.deleteOne({
  collection: "users",
  filter: { _id: "123" }
})

10. getSchema

Analyze collection structure and discover field names.

// Example
mcp.getSchema({
  collection: "users",
  sampleSize: 100
})

// Returns:
{
  "collection": "users",
  "sampleSize": 100,
  "fields": {
    "_id": {
      "types": ["ObjectId"],
      "examples": ["507f1f77bcf86cd799439011"],
      "frequency": "100/100",
      "percentage": 100
    },
    "email": {
      "types": ["string"],
      "examples": ["user@example.com"],
      "frequency": "100/100",
      "percentage": 100
    }
  }
}

Best Practices

  1. Use Schema Discovery First: Before querying, run getSchema to understand field names
  2. Handle ObjectIds: The server automatically converts string IDs to ObjectIds
  3. Use Projections: Limit returned fields to improve performance
  4. Batch Operations: Use aggregation pipelines for complex queries

Examples

Basic Usage

// Get schema first to avoid field name mistakes
const schema = await mcp.getSchema({ collection: "reports" });

// Use correct field names from schema
const reports = await mcp.find({
  collection: "reports",
  filter: { organization_id: "64ba7374f8b63db2083b2665" },
  limit: 10
});

Advanced Aggregation

const analytics = await mcp.aggregate({
  collection: "orders",
  pipeline: [
    { $match: { createdAt: { $gte: new Date("2024-01-01") } } },
    { $group: {
      _id: { $dateToString: { format: "%Y-%m", date: "$createdAt" } },
      revenue: { $sum: "$amount" },
      count: { $sum: 1 }
    }},
    { $sort: { _id: 1 } }
  ]
});

Changelog

v0.1.0

  • Initial release
  • Full MongoDB CRUD operations
  • Schema discovery tool
  • Automatic ObjectId conversion
  • TypeScript support

Made out of pain since the official MongoDB MCP didn't work for me