{"serverId":"mcp-registry/app.vercel.triageshield/triageshield","tools":[{"name":"check_vuln_report","fixed":{"name":"check_vuln_report","description":"Verify a vulnerability report's concrete, checkable claims (file paths, `file.py:123` line citations, function names) against a real GitHub repo's current default-branch state. Does NOT judge whether the described vulnerability is real or exploitable -- it only checks whether the files/lines/functions cited actually exist, which is the exact 'AI slop' failure mode (hallucinated specifics) that makes up a real share of auto-generated vuln reports. A PLAUSIBLE verdict means the claims check out, n","inputSchema":{"type":"object","required":["report","repo"],"properties":{"repo":{"type":"string","description":"A github.com/owner/name URL for the repo the report claims to be about"},"report":{"type":"string","description":"The vulnerability report text to check"}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":227,"tokensAfter":227}],"toolsChanged":1,"tokensSaved":0,"todo":[],"note":"Deterministic fixes. Changes marked verify need a human look before shipping (renames, inferred annotations, inferred types, removed text). Parameter descriptions in `todo` need to be written by someone who knows the API."}