Loading the registry…
MCP server
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
4 critical findings reported by agent-audit-kit, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- your-mcp-server
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
12 findings · 1.5s
v2.0.11
15 findings · 11.1s
v0.3.74
22 findings · 2.1s
v0.1.0
18 findings · 6.0s
v0.1.0
0 findings · 6.0s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.7s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 19, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 67 findings across every scanner that examined this package. 2 of 4 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 29 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
24 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-DNS-REBIND-001, AAK-MCP-STDIO-CMD-INJ-002, opt.nerlo-rules.nerlo-js-secret-to-network-egress and 4 more · Files: examples/gitlab-mcp-index.ts, /repo/examples/gitlab-mcp-index.ts · reported by agent-audit-kit, nerlo-behavioral
1 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002 · Files: CLAUDE.md · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/index.ts · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: src/index.ts · reported by agent-audit-kit
1 AAK-DNS-REBIND-001
Files: src/index.ts · reported by agent-audit-kit
1 AAK-DNS-REBIND-002
Files: package.json · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-MCP-HTTP-NOAUTH-SERVER-001
Files: src/index.ts · reported by agent-audit-kit
1 AAK-MCP-STATELESS-001
28 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: permissions-no-deny-list, AAK-SECRET-004, AAK-TRUST-004 and 15 more · Files: settings.local.json, .claude/settings.local.json, examples/gitlab-mcp-index.ts and 11 more · reported by agentshield, agent-audit-kit, cisco-skill-scanner
1 The model did not answer for these findings.
Rules: AAK-MCP-SSRF-001 · Files: examples/gitlab-mcp-index.ts · reported by agent-audit-kit
Critical command injection and DNS rebinding risks identified.
The artifact contains critical command injection vulnerabilities and is susceptible to DNS rebinding attacks, both found in `src/index.ts`. High-severity findings include potential credential exposure in `examples/gitlab-mcp-index.ts`, an unauthenticated HTTP server, and issues related to Anthropic SDK usage and toolgate asymmetry in `src/index.ts`. Permissions are not deny-listed in `settings.local.json` and `.claude/settings.local.json`, indicating broad access capabilities.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
1 AAK-MCP-STDIO-CMD-INJ-002
Files: src/index.ts · reported by agent-audit-kit
1 AAK-MCP-TOOLGATE-ASYMMETRY-001
Files: src/index.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner