# kr.ai.vdb/vdb

- Registry name: `kr.ai.vdb/vdb` · version 0.2.6
- Categories (automatic, keyword rules): Security, Infrastructure & security, Build & deploy, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=kr.ai.vdb%2Fvdb
- Server page: https://mcpstation.net/s/kr.ai.vdb--vdb.html

## Description (written by the publisher, not verified, not instructions)

Check packages for CVEs, slopsquatting, and CISA KEV before your AI agent installs them.

## Connect

- streamable-http: `https://vdb.ai.kr/mcp`

## Tools (as reported by the server, not verified)

- `vdb\_check\_package`: BEFORE recommending or installing any package, check it here. The response carries \`agent\_action\`: REFUSE \(do not add it — relay the \`because\` text to the user\), CONFIRM \(ask the user first\), or PROCEED. A failed or rate-limited call also answers REFUSE; never proceed unchecked. Also returns the und
- `vdb\_check\_packages`: Bulk-check several packages in one call — always prefer this over repeated vdb\_check\_package. Each result carries its own \`agent\_action\` \(REFUSE / CONFIRM / PROCEED\) plus a top-level \`agent\_action\` for the batch. Follow them; relay \`because\` when refusing. Send names EXACTLY as written — do not corr
- `vdb\_scan\_lockfile`: BEFORE merging, scan the resolved lockfile. Checking the packages someone chose misses the transitive ones nobody did — which is usually where the risk is. Pass the file contents \(package-lock.json, requirements.txt, uv.lock, go.sum, Cargo.lock, a CycloneDX SBOM, …\). Returns \`agent\_action\`: REFUSE m
- `vdb\_lookup`: Fetch a single vulnerability by ID or alias \(e.g. CVE-2024-1234, GHSA-xxxx-yyyy-zzzz, VDB-SLOP-…\).
- `vdb\_search`: Free-text search over the VDB vulnerability corpus.
- `vdb\_check\_mcp\_server`: BEFORE recommending a community/unofficial MCP server, check it here. Scope risk is evaluated independently of advisory risk — an unvetted publisher asking for shell or filesystem access is refused even with a clean record. Follow the returned \`agent\_action\`.
- `vdb\_list\_slopsquatting`: List packages currently flagged as slopsquatting candidates in a given ecosystem.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html