Sponsored by Deepsite.site

mcp-servers

Created By
assagman6 months ago
A collection of MCP servers and a CLI tool
Content

mcp-servers

A Python package providing a collection of Model-Control-Protocol (MCP) servers and a CLI tool to manage them efficiently.

Disclaimer

This project is created for personal use and does not guarantee stable behavior. It is made public solely as a reference for other programmers. The project is currently in early development, potentially unstable, and may produce undesired outcomes. Use at your own risk.


Overview

mcp-servers implements Model-Control-Protocol servers for various integrations:

  • Filesystem access
  • Brave Search integration
  • SearXNG search integration

These servers can be used by AI agents to interact with your system and external services in a controlled manner.

Pre-requisites

  • Python 3.12+
  • uv (optional but recommended package/environment manager)
  • podman or docker for container operations (e.g., running local SearXNG instance)
  • OpenRouter API key and credits (for experimentation with examples)

Installation

Package Managers

uv venv --python 3.12
source .venv/bin/activate
uv pip install --upgrade mcp-servers

Using pip

pip install --upgrade mcp-servers

Development Setup

git clone git@github.com:assagman/mcp_servers.git
cd mcp_servers
uv venv --python 3.12
source .venv/bin/activate
uv sync --extra dev

Configuration

The package requires specific configuration files in your home directory. Initialize everything at once with:

mcpserver init

This command will:

  • Create ~/.mcp_servers/.env → MCP Server HOST:PORTs, API KEYs, URLs, etc.
  • Create ~/.mcp_servers/searxng_config/settings.yml → Configuration for local SearXNG instance

⚠️ Important: You must set your own API keys in the generated .env file. They are left empty by default.

For environment variable reference, see .env.example

Usage

CLI Tool

This package provides a CLI tool (mcpserver) to manage configuration, MCP servers, and external container operations:

mcpserver -h  # Show help

Server Management

Each MCP server can be started in standard mode or detached mode. Detached mode runs the server in the background.

Filesystem Server
# Start with temporary directory
mcpserver start --server filesystem

# Operate on specific directory
mcpserver start --server filesystem --allowed-dir $(pwd)

# Custom port
mcpserver start --server filesystem --port 8765 --allowed-dir $(pwd)

# Detached mode
mcpserver start --server filesystem --detached
mcpserver stop --server filesystem  # Stop detached server
Brave Search Server

Requires BRAVE_API_KEY environment variable.

# Start server
mcpserver start --server brave_search

# Custom port
mcpserver start --server brave_search --port 8766

# Detached mode
mcpserver start --server brave_search --detached
mcpserver stop --server brave_search  # Stop detached server
SearXNG Search Server

Requires SEARXNG_BASE_URL environment variable.

# Start local SearXNG container
mcpserver run_external_container --container searxng

# Start server
mcpserver start --server searxng_search

# Custom port
mcpserver start --server searxng_search --port 8767

# Detached mode
mcpserver start --server searxng_search --detached
mcpserver stop --server searxng_search  # Stop detached server

# Stop SearXNG container
mcpserver stop_external_container --container searxng

Python API

The package can also be imported and used programmatically. See example files in examples/package_usage

Examples

The package includes examples demonstrating Agent-MCP Server usage with pydantic_ai Agents. All examples use MCPServerHTTP to connect agents with MCP Servers.

To experiment with all MCP servers:

  1. Set BRAVE_API_KEY in ~/.mcp_servers/.env (for Brave search server)
  2. Set OPENROUTER_API_KEY in ~/.mcp_servers/.env (required for all examples)
  3. Start SearXNG container (for SearXNG search server)

CLI Usage Examples

See examples/cli_usage for examples requiring MCP servers to be started via the CLI commands mentioned above.

Package Usage Examples

See examples/package_usage for examples that can be executed as-is.

Advanced Usage

Custom Configuration

You can customize server behavior by modifying configuration files:

# Edit SearXNG settings
vim ~/.mcp_servers/searxng_config/settings.yml

# Edit environment variables
vim ~/.mcp_servers/.env

Multiple Servers

You can run multiple MCP servers simultaneously by specifying different ports:

mcpserver start --server filesystem --port 8765 --detached
mcpserver start --server brave_search --port 8766 --detached
mcpserver start --server searxng_search --port 8767 --detached

Troubleshooting

Common Issues

  1. API Keys Not Working: Ensure you've set the correct API keys in ~/.mcp_servers/.env
  2. Port Conflicts: If a port is already in use, specify a different port with --port
  3. Container Issues: Use podman logs searxng or docker logs searxng to diagnose SearXNG container problems

Testing Specifications

  • Tested on macOS (arm64)
  • Python 3.12

License

This project is provided as-is with no warranty. See the LICENSE file for details.

Contributing

Contributions are welcome but not expected. If you find a bug or have a feature request, please consider forking this repo and use your own custom version.

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
WindsurfThe new purpose-built IDE to harness magic
Amap Maps高德地图官方 MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
ChatWiseThe second fastest AI chatbot™
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Serper MCP ServerA Serper MCP Server
DeepChatYour AI Partner on Desktop
CursorThe AI Code Editor
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Tavily Mcp