What is polygraph-litmus?

A local testing harness and MCP server for checking the behavior of other MCP servers. It tests for tool-output instruction attacks, unwanted data sending, sensitive-data handling, and adversarial inputs, then produces reproducible A–F evidence.

It runs behavioral safety tests through a command-line tool or MCP tool and records content-addressed results.

It helps reveal unsafe behavior before an AI agent relies on a third-party MCP server.

polygraph-litmus — MCP server 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.

agentmods

npx agentmods add mcp/polygraphso/litmus/polygraph-polygraph-litmus

Clone the repo

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

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Or install polygraph, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 MCP server.

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-litmus 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 3d ago.

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/.mcp.json · 15 lines

What it actually says

{
  "polygraph-litmus": {
    "command": "npx",
    "args": [
      "-y",
      "-p",
      "@polygraphso/[email protected]",
      "polygraphso-litmus-mcp"
    ],
    "env": {
      "POLYGRAPH_API_URL": "https://polygraph.so",
      "NEXT_PUBLIC_POLYGRAPH_NETWORK": "base"
    }
  }
}

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.

3d ago First seen · 15 lines scan A 70e98fa8ea03

Subscribe to this mod's changes

polygraph-litmus is an MCP server published in the GitHub repository polygraphso/litmus (8 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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-litmus

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 mcp servers, from other repositories

stdio-full

stdio

dev

storybook

figma

monday.com