mongodb-create-read

leonexin/mongodb-create-read

3.2

If you are the rightful owner of mongodb-create-read and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

This document provides a structured summary of the MCP server designed for MongoDB operations, focusing on creating and reading data.

Tools
2
Resources
0
Prompts
0

mongodb create read - MCP Server

Generated from MCP Scaffolding on 2025-11-10T10:09:37.110946Z

Overview

Service-agnostic MCP server with modular scaffolding

Version: 1.0.0
Transport: streamable-http
Port: 8004
Protocol: Model Context Protocol

What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). This server exposes tools and resources that can be used by MCP clients like Claude Desktop, IDEs, or custom applications.

Quick Start

This MCP server is designed to run in a Kubernetes cluster. Follow the deployment steps below to get started.

Environment Configuration

Before deploying, configure your environment variables:

  1. Copy the example environment file:

    cp .env.example .env

  2. Edit .env and fill in your credentials and configuration values:

    # Example values to configure:
JWT_SECRET=your-secret-key-here
MONGODB_URI=mongodb://your-mongodb-host:27017
# ... see .env.example for all required values

  3. Important: Never commit your .env file to version control. It's already included in .gitignore.

Connect to MCP Clients

Once deployed, MCP clients can connect via streamable-http on port 8004.

Authentication

This server uses jwt authentication.

Configure your credentials in the .env file. The server expects JWT tokens in the Authorization header:

Authorization: Bearer <your-jwt-token>

Available Tools

This MCP server exposes the following tools:

Database

Mongodb

  • mongodb_create

  • mongodb_read

Productivity

Knowledge_base

Monitoring

It_service_management

Version_control

Integrations

Using Tools

Tools are invoked through the MCP protocol by your client (e.g., Claude Desktop). Each tool can be called with parameters defined in src/templates/tools.json.

Server Configuration

Transport: streamable-http on 0.0.0.0:8004
Authentication: jwt (local)

This server was generated from a YAML configuration. To regenerate or modify the structure, update your mcpserver.yaml and run the MCP Scaffolding generator again.

Docker Deployment

Build the Image

docker build -t mongodb_create_read:1.0.0 .

Run Locally with Docker

docker run -d -p 8004:8004 \
  --name mongodb_create_read \
  mongodb_create_read:1.0.0

The server will be available on http://localhost:8004.

Kubernetes Deployment

Production-ready Kubernetes manifests are included in k8s/deployment.yaml.

Deploy to Kubernetes

# Build and push to your registry
docker build -t your-registry/mongodb_create_read:1.0.0 .
docker push your-registry/mongodb_create_read:1.0.0

# Update image in k8s/deployment.yaml, then deploy
kubectl apply -f k8s/deployment.yaml

# Check status
kubectl get deployment mongodb_create_read-deployment
kubectl get pods -l app=mongodb_create_read
kubectl logs -f -l app=mongodb_create_read

Expose the Service

# Port forwarding (for testing)
kubectl port-forward service/mongodb_create_read-service 8004:8004

In production, configure an Ingress or LoadBalancer to expose the MCP server.

Development & Customization

Implementing Your MCP Tools

The generated server includes placeholder implementations. To add your business logic:

src/persistence/datasource_tools.py - This is where you write your MCP tool implementations

  • Implement the actual logic for each tool
  • Connect to databases, APIs, or external services
  • Add data processing and business rules

Other files you may need to customize:

  • src/persistence/connections.py - Configure database connections and API clients
  • src/middleware/auth.py - Customize authentication logic and authorization rules
  • src/core/server.py - Register new tools, add custom MCP resources or prompts

Monitoring & Health Checks

The server exposes standard endpoints for monitoring:

  • Health: http://0.0.0.0:8004/health
  • Metrics: http://0.0.0.0:8004/metrics (if enabled)

Troubleshooting

Server Won't Start

  • Verify port 8004 is not already in use
  • Review logs for connection errors to external services
  • Check Kubernetes pod status: kubectl get pods -l app=mongodb_create_read

Tools Not Appearing in Client

  • Ensure the server is running and accessible
  • Verify the service is exposed correctly
  • Check MCP protocol compatibility

Authentication Errors

  • Check jwt configuration in Kubernetes secrets

Resources