io.github.GoatInAHat/toolfactory
OCI · GHCR.IO/GOATINAHAT/TOOLFACTORY · 2 COMPONENTS
Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex
Available components
Last scanned (3 hours ago)
Scores higher than 86% of OCI servers
Category Developer Tools
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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 24 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1485 tokens (~87/item across 17 items; 17 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 98% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 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.
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.
- 2 Nov 26 0
- Stability: 0.97 → pass security
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Analysed oci/ghcr.io/goatinahat/toolfactory@0.4.6
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
adopt ~56
Stop regenerating one file; it becomes the author's (recorded as manual in the lock).
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Repo-relative path of a generated file |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| adopted | string | yes | – |
No examples provided.
bootstrap-repo ~125
Prepare the GitHub repository from the local .env: the `live-tests` environment with its required reviewers and the sensitive config keys inside it, the release registries' tokens at repository scope, GitHub Pages with source = Actions, and npm's trusted publisher. Values go to `gh` on stdin and are never returned.
| Name | Type | Req | Description |
|---|---|---|---|
| dryRun | boolean | – | Print the gh invocations instead of running them |
| reviewers | array | – | GitHub logins that must approve a live run |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| commands | array | yes | – |
| dryRun | boolean | yes | – |
| environment | string | yes | – |
| manual | array | yes | The one-time human steps no API can do |
| missing | array | yes | Declared names the local .env has no value for |
| repository | string | yes | – |
| reviewers | array | yes | – |
| secrets | array | yes | Names written, never values |
No examples provided.
build ~43
Generate every selected surface in-tree from the identity file and the operation snapshot, and refresh the lock.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| deleted | array | yes | – |
| manual | array | yes | – |
| nudge | string | – | One line when a surface that published somewhere was deselected since the last tag, pointing at `unpublish`. |
| stripped | array | yes | Region files whose generated regions were emptied because their surface is no longer selected; the authored remainder stays. |
| unchanged | array | yes | – |
| written | array | yes | – |
No examples provided.
check ~43
Fail if the operation snapshot or any generated file drifted from the code (the CI drift gate).
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| ok | boolean | yes | – |
No examples provided.
coverage ~43
The operation × surface verdict matrix: native, bridged, degraded, or excluded, with reasons.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| rows | array | yes | – |
| surfaces | array | yes | – |
No examples provided.
doctor ~50
Report which upstream CLIs this machine can delegate to (git, gh, npm, uv, claude, openclaw, clawhub, hermes, uvx, agentskills, MCP Inspector, docker).
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| node | string | yes | – |
| toolfactory | string | yes | – |
| tools | object | yes | – |
No examples provided.
eject ~45
Adopt every file a surface owns, so the author takes it over entirely.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| surface | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| adopted | array | yes | – |
No examples provided.
gate ~80
Run the gate here, in order: build, the drift check, every selected surface's upstream validator, the author's checks and tests, and the credential-free host end-to-end. The same step list the generated ci.yml renders, so a project with no CI has the identical gate.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| steps | array | yes | – |
No examples provided.
init ~363
Create a new tool: dev.toolfactory/tool.json, the authored identity file, the kernel scaffold for the chosen language, and the first build of every selected surface.
| Name | Type | Req | Description |
|---|---|---|---|
| author | string | – | Author name |
| binding | string | yes | Language of the core logic: typescript or python |
| description | string | – | One-line description |
| dryRun | boolean | – | Print the gh invocations instead of running them |
| git | boolean | – | git init when the directory is not a repository yet, and make the first commit |
| keywords | array | – | Activation triggers for hosts that key off them (Kiro Powers, Agent Plugins); defaults to [name] |
| license | string | – | SPDX license identifier |
| name | string | yes | Tool name: lowercase letters, digits, hyphens, dots (Agent Plugins rule) |
| public | boolean | – | Create that repository public, not private |
| repo | string | – | owner/name of a GitHub repository to create with gh and push to |
| repository | string | – | Source repository URL (GitHub URL enables the MCP Registry name) |
| reviewers | array | – | GitHub logins that must approve a live run, when the repository gets a live tier |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| runtime | string | – | `none` creates an instruction-only skill/Codex plugin with no executable payload |
| setup | boolean | – | Run .agents/setup: render the harness adapters, install the git hooks, install dependencies |
| surfaces | array | – | Surfaces to generate. Default: the skills-first minimum — skill, agent-plugins, mcp, cli and the binding's package registry; every host-specific plugin is opt-in. |
| Name | Type | Req | Description |
|---|---|---|---|
| agentConfig | object | yes | – |
| nextSteps | array | yes | – |
| repository | object | – | – |
| written | array | yes | – |
No examples provided.
introspect ~46
Spawn the kernel MCP server, list its tools, and snapshot them to dev.toolfactory/ops.json.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| changed | boolean | yes | – |
| operations | number | yes | – |
| path | string | yes | – |
No examples provided.
package ~74
Build every release asset into dist/release/ — npm tarball, Python distributions, OpenClaw plugin tarball, plugin bundle zip, web build, coverage — by the same steps the release workflow's package job runs. Publishing stays a CI concern.
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| steps | array | yes | – |
No examples provided.
review-prompt ~99
Evaluate a prompt draft against the codex-prompt-standard rubric: anatomy sections, convention checks, and concrete directives. Draft, run this, fix what it flags, and re-run until it passes.
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | yes | The prompt draft to evaluate |
| reference | string | – | The closest reference prompt's full text, fetched per the standard (an OpenAI Codex core prompt); sections it has that the draft lacks become the bar |
| Name | Type | Req | Description |
|---|---|---|---|
| checks | array | yes | – |
| directives | array | yes | – |
| reference | object | – | – |
| sections | object | yes | – |
| verdict | string | yes | – |
No examples provided.
secrets-usage ~109
Every credential this project's surfaces need — the tool's own sensitive config keys and the release registries' tokens — with where each one is set, whether it is present locally and on GitHub, and (check) whether the registry accepts it. Never a value.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | status: the inventory. check: run each registry's own credential probe. |
| key | string | – | Only this secret |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| manual | array | yes | – |
| secrets | array | yes | – |
No examples provided.
unadopt ~50
Return an adopted file to toolfactory and regenerate it.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Repo-relative path of an adopted file |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| regenerated | string | yes | – |
No examples provided.
unpublish ~155
Retract what a deselected surface used to publish. Git is the ledger: the previous tag's dev.toolfactory/tool.json says what was selected then, and every registry row that lost its surface is checked for the version that tag published and then retracted with the registry's own CLI — or reported with the exact page, where there is no API.
| Name | Type | Req | Description |
|---|---|---|---|
| dryRun | boolean | – | List the retractions instead of running them |
| hard | boolean | – | Use the destructive retraction where one exists (npm unpublish --force) |
| ref | string | – | Diff against the tag before this ref (the release passes the tag being cut) |
| root | string | – | Project root (directory containing dev.toolfactory/) |
| Name | Type | Req | Description |
|---|---|---|---|
| dropped | array | yes | – |
| from | string | – | – |
| ran | array | – | – |
| steps | array | yes | – |
No examples provided.
validate ~66
Run each selected surface's own upstream validator (agentskills, claude plugin validate, MCP Inspector, openclaw, hermes, npm pack, uv build).
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | – | Project root (directory containing dev.toolfactory/) |
| surface | string | – | Only this surface |
| Name | Type | Req | Description |
|---|---|---|---|
| outcomes | array | yes | – |
No examples provided.
web ~38
Open this tool's web app: serves the operations page and the MCP endpoint on a free local port, opens a browser there, and returns the URL.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | – |
No examples provided.
How do I install the io.github.GoatInAHat/toolfactory MCP server?
io.github.GoatInAHat/toolfactory runs locally as a container image, launched with docker run --rm -i ghcr.io/goatinahat/toolfactory:0.4.6. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/goatinahat/toolfactory
claude mcp add goatinahat-toolfactory -- docker run --rm -i ghcr.io/goatinahat/toolfactory:0.4.6
What is the io.github.GoatInAHat/toolfactory MCP server?
io.github.GoatInAHat/toolfactory is an MCP server listed in the public MCP registry as io.github.GoatInAHat/toolfactory. Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex. This page covers its container image (ghcr.io/goatinahat/toolfactory).
Is the io.github.GoatInAHat/toolfactory MCP server safe to use?
io.github.GoatInAHat/toolfactory scores 52 out of 100 on VerifyMCP. 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 io.github.GoatInAHat/toolfactory MCP server expose?
io.github.GoatInAHat/toolfactory exposes 17 tools: init, introspect, build, check, validate, and 12 more. Their descriptions and schemas cost roughly 1,485 tokens of context every time the server is loaded.
Is the io.github.GoatInAHat/toolfactory MCP server still maintained?
io.github.GoatInAHat/toolfactory is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.