MCP Servers Vo1

This project uses Docker Compose to set up multiple Model Context Protocol (MCP) services, including Git operations, file systems, PostgreSQL databases, knowledge graph storage, and visual debugging tools, providing a complete local development environment deployment solution.

Developer tools Knowledge management and memory #Containerized Deployment #Protocol Services #Knowledge Graph #Debugging Tools

rating : 2 points

downloads : 10

update time : 2025-04-23

What are MCP servers?

MCP servers are a set of modular services that provide standardized data access interfaces for AI systems and developers. They connect data sources such as Git repositories, file systems, and databases through a unified protocol to create a secure and controllable data operation environment.

How to use MCP servers?

All services can be started with simple Docker commands. Use the built - in Inspector visual tool for management and debugging. You can obtain complete data operation capabilities without complex configuration.

Use cases

Suitable for scenarios such as AI agent development, automated data processing, and knowledge management system construction. Particularly suitable for the development of intelligent applications that require secure access to multiple data sources.

Main Features

Git repository operationsProvide full read - write, search, and historical traceability capabilities for Git repositories, supporting remote repository cloning and local repository management

Secure file systemFile operation interfaces with permission control, allowing configurable access permissions at different levels to ensure data security

Database managementPostgreSQL database connection and schema checking functions, supporting SQL queries and data operations

Knowledge graph storageA knowledge - graph - based persistent memory system supporting the storage and query of complex relational data

Visual debuggingGraphical interface to manage all MCP servers, view logs in real - time, and debug interface calls

Advantages and Limitations

Advantages

Out - of - the - box containerized deployment without complex environment configuration

Unified protocol to connect multiple data sources, reducing integration complexity

Fine - grained permission control to ensure data security

Visual debugging tools to improve development efficiency

Limitations

Currently only supports PostgreSQL databases

The memory service requires additional learning of knowledge graph concepts

The Inspector tool requires a local Node.js environment

How to Use

Environment Preparation

Ensure that Docker and Node.js environments are installed

Initialize the Repository

Run the initialization script to automatically configure the Node version and install dependencies

Start the Services

Use Docker Compose to start all MCP servers

Use the Inspector

Start the visual debugging tool to manage the servers

Usage Examples

Automated document processingBatch process documents through the file system service and manage version history with the Git service

Knowledge base constructionCombine the memory service and database service to build a structured knowledge base

Frequently Asked Questions

What if the Inspector tool fails to start?

How to add a new data source?

Where is the data stored?

Related Resources

Docker Official Documentation

Reference documentation for containerized deployment

PostgreSQL Guide

Database usage manual

MCP Protocol Specification

Model Context Protocol technical specification

🚀 MCP Server Setup Guide

This project deploys a Model Context Protocol (MCP) server using Docker Compose. It offers a comprehensive solution for managing and interacting with various data sources and services through the MCP framework.

✨ Features

Included Servers

Git: Enables reading, searching, and operating on Git repositories.
File System: Provides secure file operations with configurable access control.
PostgreSQL: Facilitates database access and schema inspection.
Memory: Implements a knowledge graph-based persistent memory system.
Inspector: A GUI tool for managing and debugging the MCP server, which can be run locally via npx.

📦 Installation

Step 1: Initialize the Repository

./scripts/init-repo.sh

This command performs the following actions:

Sets the correct Node.js version using nvm.
Globally installs the MCP Inspector.

Step 2: Start the Containerized Servers

docker compose up -d

Step 3: Start the MCP Inspector Locally

./scripts/start-inspector.sh

Step 4: Stop the MCP Inspector

./scripts/stop-inspector.sh

Step 5: Stop the Containerized Servers

docker compose down

📚 Directory Structure

docker-data/: Data directory for each MCP server.
docker-files/: Resource files for Dockerfiles.
scripts/: Utility scripts for managing services.
- init-repo.sh: Initializes the repository to set up Node.js and packages correctly.
- start-inspector.sh: Starts the MCP Inspector in the background.
- stop-inspector.sh: Stops the MCP Inspector.
- Template folders:
- template-start-mcp-server.sh: Template for creating a startup script for an MCP server.
- template-stop-mcp-server.sh: Template for creating a stop script for an MCP server.

🔧 Configuration

Each server can be configured via environment variables in the docker-compose.yml file.

💻 Accessing the Inspector

After starting, the MCP Inspector can be accessed at http://localhost:5173.

📄 Logging

Inspector logs are located at ./docker-data/inspector/inspector.log.

➕ Adding a New MCP Server

To add a new locally running (non-containerized) MCP server:

Step 1: Copy the Template Scripts

cp scripts/template-start-mcp-server.sh scripts/start-newserver.sh
cp scripts/template-stop-mcp-server.sh scripts/stop-newserver.sh
chmod +x scripts/start-newserver.sh scripts/stop-newserver.sh