Server data from the Official MCP Registry
A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.
A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.
Valid MCP server (1 strong, 3 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.
4 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-freeguy-ai-closeread-verify": {
"args": [
"closeread-verify"
],
"command": "uvx"
}
}
}From the project's GitHub README.
A verified dependency-audit verdict any AI agent can call.
A free scanner gives you raw CVEs. closeread-verify gives you the judgment: the
verdict checked against the version you actually installed, the one finding that
matters, and the exact fix. It runs as an MCP
server, so any agent (Claude Code, Cursor, your own) can call it before it ships
code and get back a checked answer, not a wall of noise.
npm auditA raw scanner and the agent itself can already produce a list of CVEs. What they
cannot manufacture is the verdict. closeread-verify is built around the one
discipline that separates a real audit from a scan:
^4.17.0 in a
manifest is not what you shipped. The tool resolves the real pinned version
from your lockfile and checks that, so it does not cry wolf over a caret
range you already patched, and does not miss a vulnerable pin a manifest-only
scan would wave through.lead: the highest-severity direct production issue, with the exact
fix. If the only findings are transitive or dev-only, the lead is honestly
null rather than a manufactured headline.That verified artifact, not the raw scan, is the product.
pip install closeread-verify
Python 3.11+. No API key, no account, no source access. Lockfile in, verdict out.
closeread-verify is the stdio command that starts the server:
closeread-verify
Add it to your MCP client. Claude Code / Cursor style (mcp.json /
claude_desktop_config.json):
{
"mcpServers": {
"closeread-verify": {
"command": "closeread-verify"
}
}
}
If you installed into a specific environment, point at that interpreter instead:
{
"mcpServers": {
"closeread-verify": {
"command": "python",
"args": ["-m", "closeread.mcp_server"]
}
}
}
| Tool | Input | Use it when |
|---|---|---|
audit_project | files: a {filename: content} map | You have a real checkout. Pass the manifest and its lockfile together (e.g. package.json + package-lock.json) so the direct-vs-transitive split is recovered. Subdir prefixes like server/package.json are allowed. |
audit_dependencies | lockfile_content: str, filename: str | You have a single manifest or lockfile and want a one-shot verdict. |
audit_repo | github_url: str | You have a public repo URL. It shallow-clones and runs the same audit. Returns an error, never a fabricated result, if the clone fails. |
The filename is load-bearing: it routes the content to the right ecosystem
parser. Supported lockfiles include package-lock.json, yarn.lock,
pnpm-lock.yaml, requirements.txt, poetry.lock, Pipfile.lock,
Gemfile.lock, composer.lock, and Cargo.lock.
Calling audit_dependencies on a requirements.txt that pins flask==0.12.0:
{
"source": "lockfile:requirements.txt",
"lead": {
"summary": "flask@0.12.0 affected by GHSA-562c-5r94-xh97",
"severity": "high",
"is_direct": true,
"dependency_kind": "prod",
"location": "requirements.txt:1",
"fix": "Update flask to a patched version (see references).",
"confidence": 0.9
},
"findings": {
"issues": [],
"direct": [
{
"kind": "dependency",
"package": "flask",
"severity": "high",
"is_direct": true,
"versions": ["0.12.0"],
"advisories": ["GHSA-562c-5r94-xh97", "GHSA-5wv5-4vpf-pj6m", "GHSA-m2qf-hxjv-5gpq"],
"locations": ["requirements.txt:1"],
"recommendation": "Update flask to a patched version (see references)."
}
],
"transitive": []
},
"counts": { "product_critical": 3, "issues": 0, "direct": 1, "transitive": 0 },
"verification": {
"basis": "each version is the INSTALLED version resolved from the lockfile, not the declared floor; advisories confirmed via OSV; result is deterministic and re-checkable",
"scanner": "closeread SCA (deterministic, no LLM)",
"advisory_source": "OSV.dev",
"as_of": "2026-06-08T12:00:00+00:00"
}
}
The agent does not get a scan to interpret. It gets a verdict to act on: bump
flask, here is the line, here is why.
Agents are starting to write, review, and ship code on their own. Before an agent
opens a PR or green-lights a deploy, it needs an answer to a simple question with
a checkable answer: is anything I depend on known-vulnerable, in the version I
actually pinned, and is it mine to fix? closeread-verify is that primitive. One
MCP call, a deterministic verdict, no LLM in the loop to hallucinate a CVE that
does not exist or miss one that does.
MIT. Built by Free Guy.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.