MCP Tools Server
by MCP-Mirror
A custom Model Context Protocol (MCP) server implementation that provides file system and command execution tools for Claude Desktop and other LLM clients. It extends LLMs' capabilities with local system access in a controlled way through well-defined tool interfaces.
Last updated: N/A
What is MCP Tools Server?
This is a FastMCP server implementation that provides a standardized way for LLMs like Claude to interact with your local file system and execute commands. It uses the Model Context Protocol (MCP) to provide context, tools, and prompts to LLM clients.
How to use MCP Tools Server?
- Install Python 3.10 or higher. 2. Install uv. 3. Clone the repository. 4. Run
uv run mcp install. 5. Get the absolute path to theuvexecutable. 6. Update your MCP server configuration in Claude Desktop to use the absolute path to theuvexecutable. 7. Connect to the MCP server from Claude Desktop using the identifier 'zbigniew-mcp'.
Key features of MCP Tools Server
execute_shell_command: Execute shell commands and get stdout/stderr results
show_file: View file contents with optional line range specification
search_in_file: Search for patterns in files using regular expressions
edit_file: Make precise changes to files with string replacements and line operations
write_file: Write or append content to files
fetch_page: Fetch the contents of a web page to a PDF and then parses it to markdown using local LLMs
Use cases of MCP Tools Server
Allowing LLMs to analyze and modify local codebases
Enabling LLMs to automate system administration tasks
Providing LLMs with access to local data for analysis and processing
Integrating LLMs with existing command-line tools
FAQ from MCP Tools Server
What is MCP?
What is MCP?
The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs).
What LLMs are compatible?
What LLMs are compatible?
While this implementation focuses on Claude Desktop, MCP is designed to be compatible with any MCP-compatible tool or LLM client.
What transport mechanisms are supported?
What transport mechanisms are supported?
MCP supports multiple transport methods for communication between clients and servers: Standard Input/Output (stdio) and Server-Sent Events (SSE).
How can I extend the server with my own tools?
How can I extend the server with my own tools?
You can easily extend this MCP server by adding new tools with the @mcp.tool decorator. Follow the pattern in server.py to create new tools that expose additional functionality to your LLM clients.
What are the security considerations?
What are the security considerations?
The MCP server provides Claude with access to your local system. Be mindful that the server executes shell commands as your user and can read, write, and modify files on your system. Consider limiting access to specific directories if security is a concern.