mcpsnoop — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by kerlenton · MCP Server · ★ 347

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is mcpsnoop safe to install? View the security audit →

About mcpsnoop

Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal. The problem The official MCP Inspector connects as its own client. It never sees the traffic between your client (Claude Desktop, Cursor, Claude Code) and your server. A breakpoint in your own server only fires once a request arrives. It can't show you the call the real client never made, or made with arguments you didn't expect. So when a tool silently isn't called, capabilities don't line up, or a call just hangs, you're back to -ing a log in and guessing. mcpsnoop sits in the real data path instead. Wrap your server command with it and watch every JSON-RPC frame in a live terminal UI as your real client and server talk. Quick start Wrap your server in your client's MCP config: Everyth

bubbleteaclaudeclicodexcursordebuggingdevtoolsgolangmcpmodel-context-protocol

Quick Facts

Stars347
Forks36
LanguageGo
CategoryMCP Server
LicenseMIT
Quality Score72.7990107989769/100
Open Issues8
Last Updated2026-09-11
Created2026-06-27
Platformsclaude-code, cli, codex, go, mcp
Est. Tokens~16k

mcpsnoop alternative? Top 6 similar tools

Looking for a mcpsnoop alternative? If you're comparing mcpsnoop with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agent-deck by asheshgoplani · ⭐ 935

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • gob by juanibiapina · ⭐ 72

    Process manager for AI agents (and humans)

  • agentsys by agent-sh · ⭐ 984

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • ClaudeR by IMNMV · ⭐ 337

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

  • gptree by travisvn · ⭐ 290

    A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or c

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Go Agent Tools

Frequently Asked Questions

What is mcpsnoop?

mcpsnoop is Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.. It is categorized as a MCP Server with 347 GitHub stars.

What programming language is mcpsnoop written in?

mcpsnoop is primarily written in Go. It covers topics such as bubbletea, claude, cli.

How do I install or use mcpsnoop?

You can find installation instructions and usage details in the mcpsnoop GitHub repository at github.com/kerlenton/mcpsnoop. The project has 347 stars and 36 forks, indicating an active community.

What license does mcpsnoop use?

mcpsnoop is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to mcpsnoop?

The top alternatives to mcpsnoop on Agent Skills Hub include agent-deck, agnix, gob. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools