litmus MCP server
io.github.polygraphso/litmuspolygraphsostreamable-httpv0.36.0Scanned
Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the litmus MCP server can do
The litmus MCP server is published by the GitHub account polygraphso. It has 3 tools. It can create or change data (1 tool: request_grade), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (check_server, list_servers and request_grade).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 21, 2026, version 0.36.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 1Claude Code: ask
request_gradeHosted grading is discontinued.Reads text others writeNo findings
Why it is in this group
- The name "request_grade" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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>.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
check_serverRead a server's published behavioral grade (A-F) from polygraph.so in under a second; no execution.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
list_serversServers with a published polygraph grade, sorted A-first then by ref.Reads text others writeNo findings
Why it is in this group
- The name "list_servers" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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`.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:09 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 404.
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 0.36.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http litmus https://polygraph.so/api/mcpclaude mcp add --transport http litmus https://polygraph.so/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__litmus__check_server",
"mcp__litmus__list_servers"
],
"ask": [
"mcp__litmus__request_grade"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as litmus. Review it before you use it.
Capability tags behind 3 rules
- mcp__litmus__check_server untrusted-input
- mcp__litmus__list_servers untrusted-input
- mcp__litmus__request_grade untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.polygraphso/litmus/verify?hash=5cb51e0932c88aa0a1b4cac68f4a63581af53fff22d31f4792e3cd58ca679612" | jq -e '.changed == false'Pinned hash 5cb51e0932c8, from Oct 21, 2026, 19:26 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.polygraphso/litmus/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.polygraphso/litmus)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.
litmus MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the litmus MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the litmus MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the litmus MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the litmus MCP server have?
- 3 tools: 1 write, 2 read. request_grade, check_server and list_servers.
Does the litmus MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the litmus MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the litmus MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.