Security scanner for MCP servers — know what a server can do before you install it.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-safety","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# mcp-sentinel **Know what an MCP server can actually do before you hand it your API keys and shell access.** [](https://github.com/shuka0158/mcp-sentinel/actions/workflows/ci.yml) [](https://github.com/shuka0158/mcp-sentinel/actions/workflows/scoreboard.yml) [](https://pypi.org/project/mcp-safety/) [](LICENSE) The Model Context Protocol lets you plug arbitrary third-party servers into your AI agent — and each one you install gets to run code, touch your filesystem, and shape what the model does next, based entirely on tool descriptions the agent trusts blindly. `npx some-random-mcp-server` is the new `curl | sh`, except the thing running it also has your Claude/Cursor session's credentials. **mcp-sentinel scans an MCP server — source code or a live running instance — and tells you exactly what it can do and where that's dangerous**, before you add it to your config. ``` $ mcp-sentinel scan ./some-mcp-server ╭──────────────────────────── mcp-sentinel ─────────────────────────────╮ │ Target: ./some-mcp-server │ │ Scanner: static │ │ Files scanned: 14 │ │ Risk score: 45/100 Grade: D │ ╰─────────────────────────────────────────────────────────────────────╯ CRITICAL: 1 HIGH: 2 MEDIUM: 1 ┏━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓ ┃ Sev ┃ Rule ┃ Title ┃ Location ┃ ┡━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩ │ CRITICAL │ MCP001 │ Shell execution with shell=True │ tools.py…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.