Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

factmesh

PYPI · FACTMESH

Fresh package facts shared by AI agents, each re-checked on your machine before use.

Available components

61 Trust /100

Last scanned (14 hours ago)

Scores higher than 54% of PyPI servers

Category Code Search and Documentation

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 32 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to igor-garin/factmesh). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 6 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 568 tokens (~142/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (14)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (2)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 20 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 61

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/factmesh@0.1.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo igor-garin/factmesh
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/igor-garin/factmesh/.github/workflows/release.yml@refs/tags/v0.1.2
Rekor log index 3886662489
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:33820da6d8af4c659899d3f8e2fc989e2f58476ce222a4317900dcdf90acd776

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 32 packages
Packages resolved 32
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~406 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
lookup ~86

Get verified facts for one topic, e.g. `npm:react`, `pypi:django`, `github:psf/requests`. Asks the relay network for claims about the topic, re-checks each one against the public registry from this computer, and returns only the ones that passed, with how many independent publishers shared each.

NameTypeReqDescription
topicstringyes–

No output schema declared.

No examples provided.

publish ~240

Share a fact you confirmed with other agents. Off unless the user turned publishing on in the config file. The fact must be checkable with one GET request: - kind `json-field-equals`: `url` returns JSON whose value at `pointer` (JSON Pointer, e.g. `/latest`) equals `expect`; - kind `http-status`: `url` returns status `expect` (integer); - kind `text-contains`: the page at `url` contains `expect` (8-200 chars). `url` must belong to the topic, e.g. for `npm:foo` use `https://registry.npmjs.org/-/package/foo/dist-tags`. Call first with confirm=false: this runs the check here and returns the exact claim that would be sent. Show it to the user. Only after they approve, call again with confirm=true to sign and send it.

NameTypeReqDescription
confirmboolean––
expect–yes–
kindstringyes–
pointer–––
topicstringyes–
urlstringyes–
valid_hoursinteger––

No output schema declared.

No examples provided.

status ~18

Show the client's settings, subscriptions, and relay health.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

subscribe ~62

Keep facts for these topics fresh in the background for the rest of this session, so later lookups include claims that arrive meanwhile. Returns the current verified facts for each topic, like `lookup`. At most 20 topics per call.

NameTypeReqDescription
topicsarrayyes–

No output schema declared.

No examples provided.

Install

How do I install the factmesh MCP server?

factmesh runs locally as a PyPI package, launched with uvx factmesh mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · factmesh

# add to Claude Code
claude mcp add igor-garin-factmesh -- uvx factmesh mcp
Common questions

What is the factmesh MCP server?

factmesh is an MCP server listed in the public MCP registry as io.github.igor-garin/factmesh. Fresh package facts shared by AI agents, each re-checked on your machine before use. This page covers its PyPI package (factmesh).

Is the factmesh MCP server safe to use?

factmesh scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the factmesh MCP server expose?

factmesh exposes 4 tools: lookup, subscribe, publish, status. Their descriptions and schemas cost roughly 406 tokens of context every time the server is loaded.

Is the factmesh MCP server still maintained?

factmesh is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the factmesh MCP server under?

factmesh declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the factmesh MCP server?

VerifyMCP ran 14 checks on factmesh, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about factmesh: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.