mcp-tap
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-taplist the tools exposed by my tradingview-mcp server"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-tap
Tap into any MCP server from your terminal — list tools, call them, inspect results, zero client setup required.
🎯 Why?
MCP servers are exploding in popularity (tradingview-mcp, OmniRoute, etc.) but developers have no quick way to test them from the CLI. The official MCP Inspector is a web UI that requires browser setup, and every other option means configuring a full AI client like Claude or Cursor just to verify a single tool call. mcp-tap fills this gap with a zero-config CLI that speaks the MCP JSON-RPC protocol directly over stdio.
Target audience: MCP server developers, AI agent builders, and DevOps engineers who need to quickly test, debug, and health-check MCP servers during development without launching a full AI client.
Related MCP server: MCP Inspector as MCP Server
✨ Features
✨ List all tools/resources/prompts exposed by any stdio-based MCP server
✨ Call any tool with JSON arguments and get formatted results instantly
✨ Ping/health-check an MCP server with latency measurement
✨ Rich terminal output with syntax-highlighted JSON and formatted tables
🚀 Quick Start
# Install
pip install mcp-tap
# Run
mcp-tap --help📦 Installation
From Source
git clone https://github.com/YOUR_USERNAME/mcp-tap.git
cd mcp-tap# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest -v🎬 Demo
The GIF above was recorded using Charm VHS:
vhs < demo.tape📖 Usage
# Show help
mcp-tap --help
# Common usage examples
mcp-tap --example🏗️ Architecture
graph LR
A[Input] --> B[Core Engine]
B --> C[Output]
B --> D[Plugins]
D --> E[Extensions]🤝 Contributing
Contributions are welcome! Please:
Fork the repo
Create a feature branch (
git checkout -b feature/amazing-feature)Commit your changes (
git commit -m 'Add amazing feature')Push to the branch (
git push origin feature/amazing-feature)Open a Pull Request
📄 License
MIT © 2026 — See LICENSE for details.
If this project helped you, please ⭐ star it!
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs71MIT
- AlicenseAqualityCmaintenanceEnables LLMs to inspect and test other MCP servers by listing and calling their tools, reading resources, and getting prompts. Supports stdio, SSE, and HTTP transports for both local and remote MCP server inspection.7101MIT
- AlicenseBqualityFmaintenanceA universal MCP server that automatically discovers and registers CLI tools as AI-powered agents with persona configuration, enabling any CLI tool to be used as an MCP tool.41MIT
- AlicenseNot gradedqualityCmaintenanceUniversal MCP server that wraps any CLI tool, enabling AI assistants to run commands via natural language.MIT