Skip to main content
Glama
Employee MCP Server (Mongo + AI Pipeline)

Employee MCP Server (Mongo + AI Pipeline)

Employee MCP Server (Mongo + AI Pipeline)

Architecture is now:

  1. AI Planner

  2. Mongo Executor

  3. AI Analysis Result

No SQL path is used.

MongoDB

Default URI:

mongodb://admin:password@localhost:27017

On startup, the server seeds large dummy administration-style data (1500 employees) into:

  • DB: employee_admin

  • Collection: employees

Related MCP server: NestJS MongoDB MCP Server

Common model environment

Create .env (or set environment variables):

AI_PROVIDER=nvidia
AI_TIMEOUT_MS=30000

MONGO_URI=mongodb://admin:password@localhost:27017
MONGO_DB_NAME=employee_admin
MONGO_COLLECTION=employees

OLLAMA_HOST=http://127.0.0.1:11434
OLLAMA_MODEL=qwen2.5:3b
OLLAMA_CHAT_PATH=/api/chat

OPENAI_API_KEY=
OPENAI_MODEL=gpt-4.1-mini
OPENAI_BASE_URL=https://api.openai.com

CLAUDE_API_KEY=
CLAUDE_MODEL=claude-3-5-sonnet-20241022
CLAUDE_BASE_URL=https://api.anthropic.com
CLAUDE_MAX_TOKENS=2048

NVIDIA_API_KEY=
NVIDIA_MODEL=google/gemma-4-31b-it
NVIDIA_BASE_URL=https://integrate.api.nvidia.com
NVIDIA_MAX_TOKENS=16384
NVIDIA_TOP_P=0.95
NVIDIA_ENABLE_THINKING=true

Supported providers:

  • ollama

  • openai

  • claude

  • nvidia

Run

npm install
node test-client.mjs --tests

Interactive:

node test-client.mjs

Example queries

  • Who has the highest salary?

  • Who earns the least?

  • What is the difference between highest and lowest salary?

  • What is the average salary?

  • How many employees are there?

  • List employees in Administration

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables natural language querying of MongoDB data by transforming AI agent questions into MongoDB aggregations. Supports secure data separation, semantic vector search, and advanced lookup capabilities for database interactions.
      5,291 npm
      6
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants like Claude to interact with MongoDB databases through standardized MCP tools. Supports full CRUD operations, aggregations, and natural language queries with Clean Architecture and dual transport modes (STDIO/HTTP).
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact natively with MongoDB databases, including schema discovery, CRUD operations, aggregation pipelines, and index management via natural language.
      21 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with MongoDB databases through natural language, supporting document CRUD, aggregation, collection listing, and statistics.
      157,916 npm
      Apache 2.0