Grade MCP servers A–F with the open behavioral litmus: reproducible, content-addressed evidence.
MCPpedia last refreshed this data
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-polygraphso-litmus": {
"args": [
"-y",
"pnpm"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This is the source for @polygraphso/litmus, the open behavioral litmus harness for MCP servers from polygraph.so.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'pnpm' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
pnpm: Path traversal in configDependencies env lockfile allows symlink creation outside node_modules/.pnpm-config
## Summary `pnpm` accepts package names from the env lockfile `configDependencies` section and uses those names directly when creating config dependency symlinks under `node_modules/.pnpm-config`. A malicious repository can commit a crafted `pnpm-lock.yaml` whose env-lockfile document contains a traversal-shaped config dependency name such as `../../PWNED_CFGDEP`. During `pnpm install`, pnpm installs the config dependency and creates a symlink at a path derived from that name. In local testin
pnpm: Path traversal in configDependencies env lockfile allows symlink creation outside node_modules/.pnpm-config
## Summary `pnpm` accepts package names from the env lockfile `configDependencies` section and uses those names directly when creating config dependency symlinks under `node_modules/.pnpm-config`. A malicious repository can commit a crafted `pnpm-lock.yaml` whose env-lockfile document contains a traversal-shaped config dependency name such as `../../PWNED_CFGDEP`. During `pnpm install`, pnpm installs the config dependency and creates a symlink at a path derived from that name. In local testin
pnpm: `patch-remove` could delete project-selected files outside the patches directory
## Summary The `patch-remove` deletion-scope issue tracked as GHSA-72r4-9c5j-mj57 / CAND-PNPM-030 has been addressed in pnpm. A crafted patch entry could resolve outside the configured patches directory and cause `pnpm patch-remove` to delete an arbitrary reachable file. This patch validates the configured directory and every resolved target before unlinking anything, then deletes the final directory entry without following it. ## Security boundary - Traversal and absolute paths that resolve
pnpm: `patch-remove` could delete project-selected files outside the patches directory
## Summary The `patch-remove` deletion-scope issue tracked as GHSA-72r4-9c5j-mj57 / CAND-PNPM-030 has been addressed in pnpm. A crafted patch entry could resolve outside the configured patches directory and cause `pnpm patch-remove` to delete an arbitrary reachable file. This patch validates the configured directory and every resolved target before unlinking anything, then deletes the final directory entry without following it. ## Security boundary - Traversal and absolute paths that resolve
pnpm: Hoisted install imports lockfile alias outside node_modules
## Summary The hoisted dependency alias issue tracked as GHSA-fr4h-3cph-29xv / CAND-PNPM-059 has been addressed in both pnpm and pacquet. A crafted lockfile alias could be joined directly under a hoisted `node_modules` directory. Traversal aliases could escape that directory, while reserved aliases such as `.bin` or `.pnpm` could overwrite pnpm-owned layout. This patch validates package-name semantics and path containment before graph insertion or filesystem work. ## Security boundary - The
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in other
Pi Coding Agent extension (CLI-first) — routes bash/read/grep/find/ls through lean-ctx CLI for strong token savings. Optional MCP bridge can register advanced tools.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server
MCP server for letmepost.dev. Publish across 8 social platforms from any agent.
MCP Security Weekly
Get CVE alerts and security updates for io.github.polygraphso/litmus and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The open behavioral litmus harness for MCP servers — grade A–F, reproducible.
# -p is required: the package ships three bins, so npx must be told which to run
npx -y -p @polygraphso/litmus polygraphso-litmus litmus npm/@modelcontextprotocol/server-filesystem
Point it at an npm ref, a pypi ref, a github/owner/repo ref (cloned, built, and run sandboxed —
Docker required; the grade pins the commit SHA), an https:// MCP endpoint, or a local entry
file. The harness connects
the way an agent would, fingerprints the exact tool surface, runs the four probe categories, and
prints the grade with the findings behind it — plus a deterministic evidence bundle on disk.
It runs the target's code (egress is Docker-sandboxed; without Docker, C-02 is skipped and the
grade caps at B), takes ~20–60s, and exits non-zero on D/F so it scripts anywhere. To dispute any
published grade, re-run this same command against the same server — open and deterministic means a
re-run reproduces the grade, or refutes it.
Looking up a grade someone already published takes under a second and runs nothing: the
polygraph.so index, or check_server from the MCP tools below.

The package ships a stdio MCP server (polygraphso-litmus-mcp) for any MCP-capable client:
check_server — read a server's published grade in under a second (no execution); the
pre-flight check before recommending or installing a server.list_servers — every server with a published grade, sorted A-first.request_grade — queue an ungraded server for polygraph.so's public grading (free).run_litmus — grade a server now: the full harness, grade + evidence returned to the agent.run_skill_litmus — grade a Claude Code / Agent Skill (static scan, A/B/D/F).verify_attestation — read the onchain proof behind a published grade (EAS on Base).In Claude Code, the plugin wires the server plus two commands in one step:
/plugin marketplace add polygraphso/
... [View full README on GitHub](https://github.com/polygraphso/litmus#readme)