Configurable Command MCP Server

A flexible MCP server that executes arbitrary command-line tools defined in a configuration file.

A flexible Model Context Protocol (MCP) server that allows you to define and execute arbitrary command-line tools through configuration files. Perfect for giving Claude Desktop access to specific command-line utilities in a secure, controlled manner.

- 🛠️Configuration-driven: Define tools via JSON without modifying code
- 🔒Secure execution: Parameter sanitization, directory restrictions, and command allowlisting
- ⚡Rate limiting: Prevent abuse with configurable execution limits
- 📝Parameter validation: Type checking, patterns, and required/optional parameters
- 🎯Directory scoping: Restrict tool execution to specific directories
- ⏱️Timeout control: Configurable execution timeouts per tool
- 📊Output management: Size limits and structured result formatting

1. Create the project directory and install dependencies

cd /Users/dewoller/code/generic_mcp npm install

Edit thetools.jsonfile to define your command-line tools. The file is already configured with useful examples like:

- list_files: List directory contents
- grep_search: Search for patterns in files
- word_count: Count lines/words/characters
- git_status: Check git repository status
- find_files: Find files by pattern
- And more!

Add the following to your Claude Desktop configuration file:

macOS:~/Library/Application Support/Claude/claude_desktop_config.json

{ "mcpServers": { "command-executor": { "command": "node", "args": ["/Users/dewoller/code/generic_mcp/dist/index.js"], "env": { "CONFIG_PATH": "/Users/dewoller/code/generic_mcp/tools.json" } } } }

After saving the configuration, restart Claude Desktop to load the MCP server.

This will test several tools and show you their output.

# Run in development mode (with TypeScript) npm run dev # Or run the built version npm start

Once configured, you can ask Claude to use these tools:

- "List all JavaScript files in my code directory"
- "Search for TODO comments in the project"
- "Show me the git status"
- "Count lines in all Python files"
- "Find all markdown files"

{ "name": "my_tool", "description": "Description for Claude", "command": "actual-command", "args": ["-flag", "{parameter}"], "parameters

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Paid remote MCP for CLI tool MCP, structured receipts, usage logs, and audit-ready evidence for agent and CI workflows.

Clean and audit messy MCP setups: stale servers, unused tools, context-heavy MCPs, outdated packages, and safe repair plans.

An MCP Server for the GitHub Actions API, enabling AI assistants to manage and operate GitHub Actions workflows.

Read-first Jenkins MCP server in Go for agent-driven build debugging. 20 tools including compare_builds, flaky-test detection, JUnit/Ginkgo failure parsing, and disk-cached console logs with on-disk path handoff. Write tools (trigger/stop/cancel) gated by JENKINS_MCP_READONLY env var.

A Python implementation of a Model Context Protocol server for interacting with Kestra.

Execute make targets from any Makefile in a safe and controlled environment.

Exposes Makefile targets as callable tools for AI assistants.

A Python-based server to install and configure other MCP servers from PyPI, npm, or local directories.

Orchestration tool for managing multiple MCP servers with a Docker Compose-style interface and a unified HTTP proxy.