Skip to main content
mcp-probe - MCP Servers | SkillsLLM
Home MCP Servers mcp-probe A Model Context Protocol (MCP) client library and debugging toolkit in Rust. This foundation provides both a production-ready SDK for building MCP integrations and the core architecture for an interactive debugger.
mcp mcp-client mcp-server model-context-protocol model-context-protocol-servers
# Add to your Claude Code skills
git clone https://github.com/conikeec/mcp-probe
🔍 MCP Probe - Advanced MCP Protocol Debugger & Interactive Client
MCP Probe is a powerful Terminal User Interface (TUI) for debugging, testing, and interacting with Model Context Protocol (MCP) servers. It provides an intuitive, feature-rich alternative to command-line MCP inspectors with real-time protocol analysis, capability discovery, and interactive tool execution.
┌─────────────────────────────────────────────────────────────────────────────────┐
│ 🔍 MCP PROBE ARCHITECTURE │
├─────────────────────────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │
│ │ 🖥️ TUI │ │ 🔌 Transport │ │ 🔧 MCP Server │ │
│ │ Interface │◄──►│ Layer │◄──►│ (Any impl.) │ │
│ │ │ │ │ │ │ │
│ │ • Capabilities │ │ • HTTP/SSE │ │ • Tools (373+) │ │
│ │ • Search │ │ • WebSocket │ │ • Resources │ │
│ │ • Response View │ │ • STDIO │ │ • Prompts │ │
│ │ • Debugging │ │ • TCP │ │ │ │
│ └─────────────────┘ └─────────────────┘ └─────────────────┘ │
│ │ │ │ │
│ ▼ ▼ ▼ │
│ ┌─────────────────────────────────────────────────────────────────────────────┤
│ │ 📊 REAL-TIME PROTOCOL ANALYSIS │
│ │ • Message Tracing • Session Management • Error Detection │
│ │ • JSON Validation • Response Formatting • Performance Metrics │
│ └─────────────────────────────────────────────────────────────────────────────┘
│ │
└─────────────────────────────────────────────────────────────────────────────────┘
Sign in with GitHub to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
🚀 Why MCP Probe?
vs. Traditional MCP Inspector Tools | Feature | Traditional CLI Tools | MCP Probe TUI |
| ------------------------ | ---------------------- | ---------------------------------------------- |
| Capability Discovery | Manual JSON parsing | 🎯 Interactive browsing with search |
| Tool Execution | Complex curl commands | 🖱️ Point-and-click with parameter forms |
| Response Analysis | Raw JSON dumps | 📊 Multi-format viewer (Tree/Summary/Raw) |
| Error Debugging | Scattered logs | 🔍 Centralized error tracking with suggestions |
| Session Management | Stateless commands | 💾 Persistent sessions with history |
| Multi-Transport | Single transport focus | 🔌 HTTP/SSE, WebSocket, STDIO, TCP support |
| Real-time Monitoring | Snapshot-based | ⚡ Live protocol stream analysis |
Key Advantages
🎮 Interactive : Navigate 373+ tools with fuzzy search and auto-completion🔍 Visual : Color-coded responses, scrollable viewers, progress indicators📊 Analytical : Built-in protocol validation, message correlation, timing analysis🛠️ Developer-Friendly : Session export, parameter templates, debugging hints🚀 Fast : Rust-powered performance with async I/O and efficient TUI rendering
📦 Installation MCP Probe offers multiple installation methods for your convenience:
📥 Pre-built Binaries (Recommended)
Linux (x86_64) : mcp-probe-x86_64-unknown-linux-gnu.tar.gzLinux (ARM64) : mcp-probe-aarch64-unknown-linux-gnu.tar.gzmacOS (Intel) : mcp-probe-x86_64-apple-darwin.tar.gzmacOS (Apple Silicon) : mcp-probe-aarch64-apple-darwin.tar.gzWindows (x86_64) : mcp-probe-x86_64-pc-windows-msvc.zip
🌐 One-liner Install (Linux/macOS) curl -fsSL https://raw.githubusercontent.com/conikeec/mcp-probe/master/install.sh | bash
Custom installation directory:
curl -fsSL https://raw.githubusercontent.com/conikeec/mcp-probe/master/install.sh | INSTALL_DIR=~/.local/bin bash
Install specific version:
curl -fsSL https://raw.githubusercontent.com/conikeec/mcp-probe/master/install.sh | VERSION=v0.1.55 bash
🍺 Homebrew (macOS/Linux) # Add the tap
brew tap conikeec/tap
# Install mcp-probe
brew install mcp-probe
# Or in one command
brew install conikeec/tap/mcp-probe
📦 Cargo Install Note : The binary will be named mcp-probe even though the crate is mcp-cli.
🔨 From Source # Clone the repository
git clone https://github.com/conikeec/mcp-probe.git
cd mcp-probe
# Build and install
cargo build --release
cargo install --path .
# Or run directly
cargo run -- --help
🛡️ Verification All binaries are provided with SHA256 checksums. You can verify your download:
# Download checksum file
curl -LO https://github.com/conikeec/mcp-probe/releases/latest/download/mcp-probe-x86_64-unknown-linux-gnu.tar.gz.sha256
# Verify (Linux/macOS)
sha256sum -c mcp-probe-x86_64-unknown-linux-gnu.tar.gz.sha256
# Verify (macOS alternative)
shasum -a 256 -c mcp-probe-x86_64-apple-darwin.tar.gz.sha256
Quick Start # Test with a local MCP server
cargo run -- debug --http-sse http://localhost:3000
# Connect to remote server
cargo run -- debug --http-sse https://api.example.com/mcp
# Use WebSocket transport
cargo run -- debug --websocket ws://localhost:8080/mcp
# STDIO mode for local development
cargo run -- debug --stdio python my_mcp_server.py
🎯 Section 1: MCP Client Usage MCP Probe serves as a comprehensive MCP client for developers and integrators who need to interact with MCP servers programmatically or interactively.
🔧 Client Configuration # Basic connection with default settings
mcp-probe debug --http-sse http://localhost:3000
# Advanced configuration
mcp-probe debug \
--http-sse http://localhost:3000 \
--timeout 30 \
--max-retries 3 \
--session-file my_session.json
💡 Interactive Workflow ┌─────────────────────────────────────────────────────────────────────────────────┐
│ 🎮 INTERACTIVE CLIENT WORKFLOW │
├─────────────────────────────────────────────────────────────────────────────────┤
│ │
│ 1️⃣ DISCOVERY PHASE │
│ ┌─────────────────────────────────────────────────────────────────────────┐ │
│ │ ┌─ Connection ─┐ ┌─ Capabilities ─┐ ┌─ Search & Filter ─┐ │ │
│ │ │• Auto-detect │ │• Tools: 373 │ │• Fuzzy matching │ │ │
│ │ │• Protocol │ │• Resources: 1 │ │• Category filter │ │ │
│ │ │• Session ID │ │• Prompts: 3 │ │• Real-time index │ │ │
│ │ └──────────────┘ └─────────────────┘ └───────────────────┘ │ │
│ └─────────────────────────────────────────────────────────────────────────┘ │
│ ▼ │
│ 2️⃣ INTERACTION PHASE │
│ ┌─────────────────────────────────────────────────────────────────────────┐ │
│ │ ┌─ Parameter Input ─┐ ┌─ Execution ─┐ ┌─ Response Analysis ─┐ │ │
│ │ │• Smart forms │ │• Real-time │ │• Multi-format view │ │ │
│ │ │• Type validation │ │• Progress │ │• Error highlighting │ │ │
│ │ │• Auto-completion │ │• Correlation │ │• Export options │ │ │
│ │ └───────────────────┘ └──────────────┘ └─────────────────────┘ │ │
│ └─────────────────────────────────────────────────────────────────────────┘ │
│ ▼ │
│ 3️⃣ ANALYSIS PHASE │
│ ┌─────────────────────────────────────────────────────────────────────────┐ │
│ │ ┌─ Session Review ─┐ ┌─ Error Analysis ─┐ ┌─ Export & Share ─┐ │ │
│ │ │• Message history │ │• Root cause hints │ │• JSON export │ │ │
│ │ │• Timing metrics │ │• Fix suggestions │ │• Session replay │ │ │
│ │ │• Protocol trace │ │• Debug logs │ │• Report sharing │ │ │
│ │ └─────────────────────└───────────────────┘ └─────────────────┘ │ │
│ └─────────────────────────────────────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────────────────┘
🔍 Smart Capability Discovery Fuzzy Search Engine : Find tools instantly among hundreds of capabilities
# Search examples (press '/' to activate)
/github
56,706
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
AI Agents ai-agents anthropic
An open-source AI agent that brings the power of Gemini directly into your terminal.
AI Agents ai ai-agents
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
AI Agents agent-skills ai-agents
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
MCP Servers llm mcp
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
MCP Servers ai bark
