mcp-servers

Name: mcp-servers
Author: assagman

@assagman

Repository

About mcp-servers

A collection of MCP servers and a CLI tool

#ai-llm-mcp #mcp-servers #cli-tool

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-servers-assagman": {
      "command": "uv",
      "args": [
        "venv",
        "--python",
        "3.12"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-servers?

mcp-servers is a Python package that provides a collection of Model-Control-Protocol (MCP) servers and a CLI tool to manage them efficiently. It integrates with your system and external services for filesystem access, Brave Search, SearXNG, and Tavily Search, allowing AI agents to interact in a controlled manner.

How to use mcp-servers?

Install the package via uv pip install mcp-servers or pip install mcp-servers, run mcpserver init to create configuration files in ~/.mcp_servers/.env, then start a specific server with mcpserver start --server <name>. Optionally use the Python API by importing the package.

Key features of mcp-servers

CLI tool (mcpserver) to manage configuration and servers.
Supports filesystem, Brave Search, SearXNG, and Tavily Search integrations.
Start servers in standard or detached (background) mode.
Customizable ports and allowed directories for filesystem server.
Can run multiple MCP servers simultaneously on different ports.
Python API for programmatic use with pydantic_ai agents.

Use cases of mcp-servers

Allow an AI agent to read and write files on the local filesystem.
Let an AI agent perform web searches via Brave Search API.
Run a local SearXNG instance for privacy-focused federated search.
Integrate Tavily Search for AI-optimized search results.
Build multi-server setups where an agent combines file access and various search services.

FAQ from mcp-servers

What are the prerequisites for mcp-servers?

Python 3.12+ is required. uv (optional but recommended) and podman or docker for container operations like running SearXNG. An OpenRouter API key with credits is needed for the examples.

How do I configure API keys?

Run mcpserver init to generate ~/.mcp_servers/.env and ~/.mcp_servers/searxng_config/settings.yml, then set your own API keys (e.g., BRAVE_API_KEY, TAVILY_API_KEY, SEARXNG_BASE_URL, OPENROUTER_API_KEY) in the .env file.

Can I run multiple MCP servers at the same time?

Yes, you can start multiple servers on different ports using the --port option and detached mode, e.g., mcpserver start --server filesystem --port 8765 --detached and mcpserver start --server brave --port 8766 --detached.

What if a port is already in use?

Specify a different port with the --port flag when starting the server.

Is mcp-servers stable for production use?

No, this project is in early development, potentially unstable, and may produce undesired outcomes. It is provided as a reference for programmers and should be used at your own risk.