MCP.Market

Litmus MCP server

not responding
by polygraphso·io.github.polygraphso/litmus·v0.36.0·8 stars
No reviews yet

Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.

C61/100grade C
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
C61/100

full report

Adoption
Growing

8 stars36 downloads/wk

Reviews

Write one

Nobody has reviewed Litmus yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Litmus tools (3)

write = sends, deletes, buys or posts
  • check_serverFree

    Read a server's published behavioral grade (A-F) from polygraph.so in under a second; no execution. The pre-flight check before recommending or installing an MCP server. On a miss it returns not_available (unevaluated: neither safe nor unsafe) with next steps.

  • list_serversFree

    Servers with a published polygraph grade, sorted A-first then by ref. Returns up to `limit` rows starting at `offset` (default limit 25, capped at 100 per call); `grade` restricts to one letter. `summary` always covers the full graded corpus (a total plus a count per grade), regardless of `grade`, `limit`, or `offset`.

  • request_gradeFree

    Hosted grading is discontinued. This tool returns gone. Existing published grades remain available via check_server / list_servers. To grade a server yourself, run the open harness: npx -y -p @polygraphso/litmus polygraphso-litmus litmus <server_ref>.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

1 high
  • Code scan16 source files scanned25/25
  • Live reliabilityremote unreachable: Streamable HTTP error: Error POSTing to endpoint: {"error": {"code": "404", "message": "The deployment could not be found on Vercel."}}0/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 101 days ago8/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • highRemote endpoint did not respondreliability.unreachable

    Streamable HTTP error: Error POSTing to endpoint: {"error": {"code": "404", "message": "The deployment could not be found on Vercel."}}

Overall 61/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Litmus compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
61/100
higher than 16% of 48,255 servers
Tools
3
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
25%
of our recent checks; the typical remote server answers 100%
Response time
754 ms
faster than 18% of 30,031 servers
GitHub stars
8
more than 86% of 28,688 servers
Downloads a week
36
more than 26% of 12,191 servers with a package

What its tools let an agent do: 3 read

Install Litmus in Claude Code, Cursor or VS Code

claude mcp add --transport http litmus https://polygraph.so/api/mcp
Add to Cursor

What the publisher says

From the Litmus repository's README, as published. We do not edit it. Read it on GitHub

litmus

The open behavioral litmus harness for MCP servers — grade A–F, reproducible.

<!-- Badges live in a one-row table so they stay on a single line on BOTH the repo page and the GitHub Marketplace listing for the polygraph-mcp-gate action. The Marketplace stylesheet sets img { display: block }, which stacks plain inline badges into a tall vertical column; table cells lay out horizontally regardless. GitHub strips inline styles, so the cells keep their default 1px border — that boxed look is expected. Don't revert to a plain badge line. -->

Grade a server in one command

# -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.

Use it from your agent — MCP server + plugin

For grade lookups, point any MCP client at polygraph's hosted endpoint, no install:

claude mcp add --transport http polygraph https://polygraph.so/api/mcp

or the raw config:

{ "mcpServers": { "polygraph": { "url": "https://polygraph.so/api/mcp" } } }

This serves the lookup tools only (checkserver, listservers, requestgrade); grading a server yourself (runlitmus, runskilllitmus) executes its code, so it needs the local stdio install below.

The package also ships a stdio MCP server (polygraphso-litmus-mcp) with the full toolset, for any MCP-capable client:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-29downgradeA → Cscore 61: Remote endpoint did not respond

Litmus: common questions

Is Litmus MCP server safe?
With care: it is graded C, so read the findings first (61/100). Read the Litmus safety report
How do I install Litmus?
It runs remotely at polygraph.so. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Litmus need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Litmus maintained?
The last commit was 107 days ago (2026-07-20). The latest release is v0.36.0.
Is Litmus up?
25% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Litmus compare with other MCP servers?
safety score 61/100 (higher than 16% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.