@polygraphso/litmus

MCPcommunity
v0.12.1UnknownApache-2.0Updated 14d agonpmGitHub

Behavioral litmus harness for MCP servers — grade a server A–F (tool-output injection, egress, sensitive-data, adversarial-input) with reproducible, content-addressed evidence. Ships a CLI and an MCP server with a run_litmus tool for AI agents.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
2kDownloads/wk
14d agoLast update
Package
AuthorUnknown
LicenseApache-2.0
Version0.12.1
Sourcenpm+mcp-registry
npm@polygraphso/litmus
GitHubpolygraphso/litmus
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/25
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/10
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
—npm provenance (Sigstore)+0/5
→ Publish from GitHub Actions with the --provenance flag
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 0 resolved · none vulnerable
Tool surface—
Security scan✓ Cleanv0.12.1 · 11d ago
CODEdist/chunk-OGOFUBLN.jsDynamic require of a computed module name
EvalsNone
IndexedJun 19, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

Behavioral litmus harness for MCP servers — grade a server A–F (tool-output injection, egress, sensitive-data, adversarial-input) with reproducible, content-addressed evidence. Ships a CLI and an MCP server with a run_litmus tool for AI agents.

Keywords
polygraphmcpmodel-context-protocoltrustai-agentssecuritylitmus