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.

factoryhub

NPM · FACTORYHUB

Find, read, validate, export and run AI factories with your own model. Runs stop at human decisions.

Available components

74 Trust /100

Last scanned (18 hours ago)

Scores higher than 49% of npm servers

Category AI and Machine Learning

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 3 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency71
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Cryptographically verified build provenance (signed, bound to Mindburn-Labs/factoryhub). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 5 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1693 tokens (~80/item across 21 items; 6 tools + 15 resources), lean.Pass
  • 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • 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.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
  • 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.

  • 17 Nov 26 −5
    • Source repository: pass → fail ▼ security
    • Security disclosure: pass → unverified ▼ functional
  • 16 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 64

    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 npm/factoryhub@0.1.1

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 npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo Mindburn-Labs/factoryhub
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Mindburn-Labs/factoryhub/.github/workflows/release.yml@refs/tags/v0.1.1
Rekor log index 3912241793
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:381ad4cd221cba1e934ba9442af139262a1ca77ca3cfe3c3e32d533b1f8f065149596c449d0ef78c66f6354deb6b0a6fc79240c3648ba1fce84eefa76

Background: How many MCP packages publish verified provenance →

Dependencies 3 packages
Packages resolved 3
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~687 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
export_skill ~130

Turns a factory into an Agent Skill folder: <id>/SKILL.md (what it produces, inputs to collect, every step and who does it, where to stop and ask the person to approve) and <id>/factory/ (the files unchanged, plus a foreman written from the flow when the author wrote none). With out_dir, writes the folder there; without, returns SKILL.md and the file list.

NameTypeReqDescription
idstring––
out_dirstring––
overwriteboolean––
pathstring––
sourcestring––

No output schema declared.

No examples provided.

get_factory ~87

Reads one factory: its summary (inputs, steps in order, agents, tools, checks), its bundle SHA-256, and the full text of every file. Give an id (local or, with source "hub", published) or a path to a folder or bundle .json.

NameTypeReqDescription
idstring––
pathstring––
sourcestring––

No output schema declared.

No examples provided.

list_factories ~86

Lists AI factories: the house factories and folders named in FACTORYHUB_FACTORIES (source "local"), or the published catalogue on factoryhub (source "hub", which needs FACTORYHUB_ACCESS_KEY while the site is in private preview). Filters by words in the id, title, description or tags.

NameTypeReqDescription
querystring––
sourcestring––

No output schema declared.

No examples provided.

resume_run ~125

Continues a run that is waiting at a human decision. Call it only with the person's own answer: approve, reject (ends the run with no result), or revise with a note saying what to change. Pass the seen_sha256 and approval_id from the waiting result, so the decision applies to the exact text the person saw. Returns at the next decision or when the run ends.

NameTypeReqDescription
approval_idstringyes–
decisionstringyes–
notestring––
run_idstringyes–
seen_sha256stringyes–

No output schema declared.

No examples provided.

run_factory ~173

Runs a factory on this machine with the model key set in this server's environment (ANTHROPIC_API_KEY, OPENAI_API_KEY or OPENROUTER_API_KEY), or a local OpenAI-compatible server (provider "ollama" or base_url, with model). It can take minutes. It returns when the run is done, fails, or reaches a human decision: then it returns run_id, the text to show, seen_sha256 and approval_id. Show the person the text, get their decision, and call resume_run. Never decide for them.

NameTypeReqDescription
base_urlstring––
idstring––
inputsobject––
modelstring––
pathstring––
providerstring––
sourcestring––

No output schema declared.

No examples provided.

validate_factory ~86

Checks a factory with the engine's parser, without a key or a model: every problem, every tool this runner lacks, and whether it runs here. Give a path to a folder or bundle .json, an id, or the files themselves as a map of path to text.

NameTypeReqDescription
filesobject––
idstring––
pathstring––

No output schema declared.

No examples provided.

Install

How do I install the factoryhub MCP server?

factoryhub runs locally as an npm package, launched with npx -y factoryhub mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · factoryhub

# add to Claude Code
claude mcp add mindburn-labs-factoryhub -- npx -y factoryhub mcp
Common questions

What is the factoryhub MCP server?

factoryhub is an MCP server listed in the public MCP registry as io.github.Mindburn-Labs/factoryhub. Find, read, validate, export and run AI factories with your own model. Runs stop at human decisions. This page covers its npm package (factoryhub).

Is the factoryhub MCP server safe to use?

factoryhub scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 factoryhub MCP server expose?

factoryhub exposes 6 tools: list_factories, get_factory, validate_factory, export_skill, run_factory, resume_run. Their descriptions and schemas cost roughly 687 tokens of context every time the server is loaded.

Is the factoryhub MCP server still maintained?

factoryhub 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 factoryhub MCP server under?

factoryhub 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 factoryhub MCP server?

VerifyMCP ran 14 checks on factoryhub, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about factoryhub: Security disclosure 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 an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.