mcpsnoop MCP Server
kerlenton/mcpsnoop
[](https://agentrank-ai.com/tool/kerlenton--mcpsnoop/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Wireshark for MCP. A transparent proxy between your AI client and MCP server. Watch every call live in your terminal, fail CI on what it finds, export OpenTelemetry spans.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
kerlenton/mcpsnoop is a Go MCP server licensed under MIT. Wireshark for MCP. A transparent proxy between your AI client and MCP server. Watch every call live in your terminal, fail CI on what it finds, export OpenTelemetry spans. Topics: mcp, model-context-protocol, bubbletea, claude, cli, codex, cursor, debugging, devtools, golang, proxy, terminal, tui, ci, github-actions, observability, opentelemetry.
Ranked #18 out of 24842 indexed tools.
In the top 1% of all indexed tools.
Has 21 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
361 stars → growing community
Last commit 4d ago → actively maintained
74/74 issues closed → responsive maintainer
21 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/kerlenton--mcpsnoop/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/kerlenton--mcpsnoop/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/kerlenton--mcpsnoop" alt="AgentRank"></a> Matched Queries
From the README
<p align="center"> </p> **Wireshark for MCP.** mcpsnoop sits between your AI client and your MCP server and records every JSON-RPC frame they exchange, with no change to either side. Watch it live in your terminal, fail CI on what it finds, or send it to your tracing backend as OpenTelemetry spans. <p align="center"> </p> ## The problem The official [MCP Inspector](https://github.com/modelcontextprotocol/inspector) connects as its own client, so it never sees what *your* client (Cursor, Claude Code, Codex) actually sends your server. And anything that waits for a request to arrive can't show the call the model never made, or made with the wrong arguments. When a tool silently isn't called, capabilities don't line up, or a call just hangs, you're left digging through logs and guessing. **mcpsnoop sits in the real data path instead.** Wrap your server command with it and watch every JSON-RPC frame live, as your real client and server talk. ## In CI This page is also the listRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.