mcp-reticle
The Wireshark for the Model Context Protocol (Reticle) intercepts, visualises, and profiles MCP JSON-RPC traffic in real time — designed for microsecond-level overhead.
README
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/labterminal/mcp-reticle/main/frontend/src/assets/logo-white.png" /> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/labterminal/mcp-reticle/main/frontend/src/assets/logo.png" /> <img src="https://raw.githubusercontent.com/labterminal/mcp-reticle/main/frontend/src/assets/logo.png" alt="Reticle Logo" width="120" /> </picture> </p>
<h1 align="center">RETICLE</h1>
<p align="center"> <strong>The Wireshark for the Model Context Protocol (MCP)</strong> </p>
<p align="center"> <a href="LICENSE"> <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT" /> </a> <a href="https://www.npmjs.com/package/mcp-reticle"> <img src="https://img.shields.io/npm/v/mcp-reticle.svg" alt="npm" /> </a> <a href="https://pypi.org/project/mcp-reticle/"> <img src="https://img.shields.io/pypi/v/mcp-reticle.svg" alt="PyPI" /> </a> <a href="https://github.com/labterminal/mcp-reticle/wiki"> <img src="https://img.shields.io/badge/docs-wiki-informational" alt="Docs (Wiki)" /> </a> <img src="https://img.shields.io/badge/Platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey.svg" alt="Platform" /> </p>
<p align="center"> <em>See what your agent sees.</em> </p>
<p align="center"> Reticle intercepts, visualizes, and profiles MCP JSON-RPC traffic in real time — designed for microsecond-level overhead. </p>
<p align="center"> <a href="#quick-start">Quick start</a> · <a href="#installation">Install</a> · <a href="#documentation">Docs</a> · <a href="#security--privacy">Security</a> · <a href="#contributing">Contributing</a> </p>
<p align="center"> <img src="https://raw.githubusercontent.com/labterminal/mcp-reticle/main/frontend/src/styles/reticle.png" alt="Reticle Screenshot" width="900" /> </p>
What is Reticle?
Reticle is a proxy + UI for debugging MCP integrations:
- inspect raw JSON-RPC messages (requests / notifications / responses)
- correlate request ↔ response instantly
- profile latency and token estimates
- capture server stderr and crashes
- record sessions and export logs
Supported transports: stdio, Streamable HTTP, WebSocket, HTTP/SSE.
Quick start
1) Install
# npm
npm install -g mcp-reticle
# pip
pip install mcp-reticle
# Homebrew
brew install labterminal/mcp-reticle/mcp-reticle
2) Wrap your MCP server (stdio)
Replace your MCP server command with mcp-reticle run --name <name> -- <command...>.
Example (Claude Desktop-style config):
{
"mcpServers": {
"filesystem": {
"command": "mcp-reticle",
"args": ["run", "--name", "filesystem", "--", "npx", "-y", "@modelcontextprotocol/server-filesystem", "/Users/me/work"]
}
}
}
3) Launch the UI
mcp-reticle ui
Optional: log-only mode (no UI)
mcp-reticle run --log -- npx -y @modelcontextprotocol/server-memory
Optional: proxy an HTTP-based MCP server
mcp-reticle proxy --name api --upstream http://localhost:8080 --listen 3001
Installation
If you prefer building from source:
git clone https://github.com/labterminal/mcp-reticle.git
cd mcp-reticle
just build
Documentation
All guides and deep dives are in the GitHub Wiki:
- Getting started
- CLI reference
- Client configuration
- Troubleshooting
- Architecture
- Security & privacy
- Development
- Exports
CLI overview
| Command | Purpose |
|---|---|
mcp-reticle run |
Wrap stdio MCP servers and inspect traffic |
mcp-reticle proxy |
Reverse proxy HTTP/SSE/WebSocket transports |
mcp-reticle ui |
Launch the desktop UI |
mcp-reticle daemon |
Headless telemetry hub |
Full details: CLI reference
Security & privacy
Reticle can capture tool inputs/outputs and server stderr. Treat recordings and exports as sensitive artifacts.
Recommended reading: Security & privacy
Contributing
- Repo guidelines:
CONTRIBUTING.md - Dev setup and commands: Development guide
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。