Closeread Verify
Runs dependency audits that agents can actually act on. Instead of dumping raw CVE lists, it resolves the installed version from your lockfile, splits direct from transitive issues, and surfaces a single lead finding with the exact fix. Exposes three MCP tools: audit_project for multi-file checkouts, audit_dependencies for a single lockfile, and audit_repo for public GitHub URLs. Checks advisories against OSV.dev with no LLM in the loop, so the verdict is deterministic and re-checkable. Supports npm, pip, RubyGems, Composer, and Cargo lockfiles. Useful when you want an agent to gate a deploy or PR on a verified dependency verdict rather than interpret a wall of scanner noise itself.
- tools
- 3
- transport
- STDIO
- last updated
- Jun 9, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
audit_projectYou have a real checkout. Pass the manifest and its lockfile together so the direct-vs-transitive split is recovered.
You have a real checkout. Pass the manifest and its lockfile together so the direct-vs-transitive split is recovered.
No parameter schema in public metadata yet.
audit_dependenciesYou have a single manifest or lockfile and want a one-shot verdict.
You have a single manifest or lockfile and want a one-shot verdict.
No parameter schema in public metadata yet.
audit_repoYou have a public repo URL. It shallow-clones and runs the same audit.
You have a public repo URL. It shallow-clones and runs the same audit.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
closeread-verify
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.
Why this and not npm audit
A 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:
Details
- Repository
- github.com/freeguy-ai/closeread-verify
- Category
- AI & LLM Tools
- Package
closeread-verify- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
ESG MCP Serversfreminder/esg-mcp-servers31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.0stars
Cyphrexgetcyphrex/platformChecks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.0stars
TrustLayergoatgaucho/trust-layerAgent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents0stars
Intelligence Mcpgoodmeta/intelligence-mcpAgent payments ecosystem intelligence. Scans GitHub/HN/npm across AP2, ACP, x402, MPP, UCP.0stars
Gsep Mcpgsepcore/gsep-mcpAI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.0stars
DrinkedIn — licensed bar dataio.github.haim-barad/drinkedinLicensed bar data from public registers, x402. Agent-bar tools deprecated. No real alcohol.0stars