polygraph.so
§ MCP/Behavioral grade
A

npm/raven-mcp

graded version 1.12.0 · litmus-v7 · 2026-06-24

Adoption 37/100 · 2.06K npm/mo · as of 2026-06-26

C-01 Tool-output injection
pass
C-02 Permission / egress overreach
pass
C-03 Sensitive-data handling
pass
C-04 Adversarial-input handling
pass

tool-defs fingerprint · 0x41d88a…5684b

Why A: All four categories passed. No injection, no data leak, no egress overreach, and adversarial inputs were handled cleanly (A means no overreach, not no network).

Adoption signals

The 37 / 100 adoption score blends the raw signals below — downloads, stars, dependents and release velocity — normalized across every tracked server. It measures reach, not safety; the litmus grade is the safety verdict. See the methodology.

npm downloads (30d)
2,061
GitHub stars
2
Forks
0
Contributors
2
Dependents (deps.dev)
0
Last published
2026-06-22

Reproduce this grade

The harness is open and deterministic. Re-run it against the same server and compare the grade and fingerprint — a false grade is falsifiable, not merely disputable.

npx -p @polygraphso/litmus polygraphso-litmus npm/raven-mcp

Embed this badge

Drop it in a README, docs site, or package page. It always shows the current published grade and links back here.

polygraph grade A
Markdown — badge
[![polygraph](https://polygraph.so/api/badge?server=npm/raven-mcp)](https://polygraph.so/mcp/npm/raven-mcp)
HTML — badge
<a href="https://polygraph.so/mcp/npm/raven-mcp"><img src="https://polygraph.so/api/badge?server=npm/raven-mcp" alt="polygraph grade"></a>
Markdown — card
[![polygraph](https://polygraph.so/api/badge/card?server=npm/raven-mcp)](https://polygraph.so/mcp/npm/raven-mcp)