Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for MCP server authors, MCP client authors, agent harness developers, and anyone debugging 'the tool was supposed to be called but never was' or 'the call hung' mysteries in Claude Desktop / Cursor / Claude Code — the canonical replacement for `tail -f /tmp/some.log` and the right primitive for closing the gap between an MCP server's intended API and the calls a real client actually makes.
Who should use it
Who should skip it
Move on from kerlenton/mcpsnoop if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
kerlenton/mcpsnoop is tracked by RepoRadar as a mcp traffic inspector in the AI Agents section. It was first seen on 2026-07-03 and last updated on 2026-07-03. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, kerlenton/mcpsnoop is strongest on workflow potential (10.0) and practical usefulness (9.0) and weakest on maturity (6.6) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned kerlenton/mcpsnoop a composite score of 8.5 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
mcpsnoop is a transparent proxy in the real data path between your MCP client and your MCP server — the JSON-RPC frames the TUI shows include the full request payloads (tool name, arguments, file paths, auth tokens) and the full response payloads. Run mcpsnoop on the same machine that owns the client, not on a shared or multi-tenant host, and clear the TUI scrollback before sharing a screen recording or a log capture; The `mcpsnoop demo` scripted tour runs in a self-contained session but it still exercises a real MCP server–client interaction — review the `mcpsnoop --` wrap command and the demo's payload content before running on a workstation that has production MCP servers configured, and pin the demo to a non-production MCP server (e.g. a dev/test server) to keep production traffic on a different debug path; The Go single-binary install path (`go install github.com/kerlenton/mcpsnoop@latest`) requires a Go toolchain on the dev machine; for non-Go environments, use the release binary from the GitHub Releases page. The CLI's `--` separator is the only wrap-pattern contract — verify your MCP client preserves the `--` separator when launching the server (some clients strip trailing args; if you see 'command not found' on the server, check the client config first).