polygraphso
01Plugin Claude Code
Official polygraph marketplace — tools for grading and verifying MCP servers with the open litmus harness.
Plugin Claude Code
Official polygraph marketplace — tools for grading and verifying MCP servers with the open litmus harness.
Instructions file
Instructions for polygraphso/litmus, covering litmus — workspace context for claude, where to look first, what we're building (one paragraph), packaging model (do not break) and releasing.
Skill Claude CodeCodex
Always run this on every repository to set up the developer environment and fix common issues.
Skill Claude CodeCodex
Use when setting up a new Node.js project to install tooling and pre-commit hooks.
Plugin Claude Code
Grade and verify MCP servers A–F with the open polygraph litmus — tool-output injection, egress, sensitive-data, and adversarial-input checks. Bundles the polygraph skill, the polygraph-litmus MCP server, and /polygraph:grade · /polygraph:check.
MCP server Claude CodeCodexCursor +2
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 runlitmus tool for AI agents. Runs locally from the @polygraphso/litmus npm package. Needs 2 environment…
Command
Read a server's already-published polygraph grade (no run).
Command
Grade an MCP server A–F with the open polygraph litmus (runs the harness).
Skill Claude CodeCodex
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…
MCP server Claude CodeCodexCursor +2
Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only. Runs locally from the @polygraphso/litmus npm package. Needs 2 environment variables to run.