A plugin that bundles tools for testing and checking the behavioral safety of MCP servers, which provide extra capabilities to AI agents. It includes the Polygraph skill, its testing server, and commands for grading or checking servers.

It helps run A–F evaluations, inspect tool-output injection and data-handling risks, and verify published safety grades.

It packages safety evaluation and published-grade checks into one installable add-on before an agent uses an MCP server.

polygraph — Plugin by polygraphso

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add polygraphso/litmus

agentmods

npx agentmods add plugins/polygraphso/litmus/polygraph

Clone the repo

git clone --depth 1 https://github.com/polygraphso/litmus

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

polygraph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/polygraph/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "polygraph",
  "description": "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.",
  "version": "0.7.3",
  "skills": "./skills/",
  "author": {
    "name": "polygraph"
  },
  "homepage": "https://polygraph.so",
  "repository": "https://github.com/polygraphso/litmus",
  "license": "Apache-2.0",
  "keywords": ["mcp", "security", "litmus", "grading", "attestation"]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 14 lines scan A 39fcb4c18f95

Subscribe to this mod's changes

polygraph is a plugin published in the GitHub repository polygraphso/litmus (8 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security Testing agents mcp-server

polygraph

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

agent-teams

newsjack

moraine

jenkins-cli

claude-superskills

agents-market