Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Pre-install verdicts for npm packages: GO, RISKY, FAKE, or MISSING. Built for humans and AI agents.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"pkgverdict": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add pkgverdict -- docker run -i --rm ghcr.io/cloudcorprecords/pkgverdict:0.1.1 mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"pkgverdict": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"pkgverdict": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.1) reached the registry 14 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Apify MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Check an npm package before you install it. One command, one verdict: GO, RISKY, FAKE, or MISSING — in plain words your AI coding agent can read too.
pkgverdict ships as a container image on GHCR (there is no npm package named pkgverdict, so npx pkgverdict will 404 — use Docker):
docker run --rm ghcr.io/cloudcorprecords/pkgverdict check react-markdown
docker run --rm ghcr.io/cloudcorprecords/pkgverdict check unused-imports
docker run --rm ghcr.io/cloudcorprecords/pkgverdict check react-super-hooks-plus
AI assistants now pick half the packages developers install — and they hallucinate names attackers have already registered (slopsquatting), while typosquats and hijacked releases keep shipping postinstall malware. npm audit only sees published advisories, after the fact. pkgverdict checks before the install: existence, lookalike names, package age, install scripts, maintainers, downloads, and OSV advisories.
One command sets it up. In your project directory, run:
docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict init --agent claude-code
That installs the MCP server config plus the instruction snippet teaching your agent the one behavior rule: check pkgverdict before installing. Supported tools: claude-code, cursor, copilot (VS Code), windsurf, cline, and generic (init --list shows them all; --all sets up everything; --dry-run previews without writing). Restart your tool, verify with a "list your MCP tools" prompt, and the pkgverdict server should appear with 2 tools (check_package, scan_dependencies). The underlying pack lives in integrations/ if you prefer to install by hand.
# Verdict on one package (name or name@version)
docker run --rm ghcr.io/cloudcorprecords/pkgverdict check lodash
docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict scan docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict scan ./my-app --no-dev
docker run --rm ghcr.io/cloudcorprecords/pkgverdict doctor
docker run --rm ghcr.io/cloudcorprecords/pkgverdict check left-pad --json
Exit codes: 0 when everything is GO (or RISKY without --strict), 1 when a FAKE or MISSING package is found, 2 on usage errors. For CI gates that should fail on anything suspicious: pkgverdict scan --strict.
| Verdict | Meaning |
|---|---|
| GO | Established package, no red flags. Install away. |
| RISKY | Caution: install scripts, very young, obscure, deprecated, no repo/license, known advisories, or a lookalike name on an otherwise fine package. Read before installing. |
| FAKE | Looks actively bad: typosquat-shaped name on a new/obscure package, hostile install script, or a malicious advisory (MAL- id, a MAL- alias, or an OSV record whose details mark the package itself malicious/backdoored — e.g. the event-stream@3.3.6 compromise, carried under a GHSA id). Do not install. |
| MISSING | Not on the registry at all — a typo or a hallucinated name, with a "did you mean" suggestion when one fits. |
Signals come from the npm registry (metadata, downloads), the OSV database (advisories), and a bundled list of well-known packages for lookalike detection. Responses cache under ~/.cache/pkgverdict (6h metadata, 1h advisories); delete that directory to force fresh checks.
pkgverdict has exactly two distribution channels, and both are intentional:
ghcr.io/cloudcorprecords/pkgverdict, built and pushed by the Publish container workflow on each release.io.github.CloudCorpRecords/pkgverdict, whose server.json carries an OCI package only, pointing at that same GHCR image.There is no npm package, and that is the model, not a missing step. npx pkgverdict returning 404 is expected. The unscoped name in package.json exists to build the image and version the CLI; the package is marked private so a stray npm publish from a checkout fails fast instead of claiming the name, and the old template workflow that ran npm publish on every release now sits disabled at .github/workflows/publish.yml, printing this model instead of publishing. Publishing to npm later would be a maintainer decision needing a scoped name and a token with rights to it. These facts are pinned by test/distribution.test.ts, so the residue cannot quietly come back.
The GHCR image is the primary distribution: ghcr.io/cloudcorprecords/pkgverdict.
Use it as a stdio MCP server:
docker run --rm -i ghcr.io/cloudcorprecords/pkgverdict
Any CLI command can be passed after the image name instead of the default mcp argument:
docker run --rm ghcr.io/cloudcorprecords/pkgverdict <command> [args]
Point your MCP client at Docker (stdio):
{
"mcpServers": { "pkgverdict": { "command": "docker", "args": ["run", "--rm", "-i", "ghcr.io/cloudcorprecords/pkgverdict", "mcp"] } } }
Two tools: check_package (verdict on one package) and scan_dependencies (worst-first verdicts for a project's package.json).
npm install
npm run build npm test # offline fixture corpus: every verdict rule pinned to a case
MIT.