Loading the registry…
Add your description here
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.
3 critical findings reported by agent-audit-kit. 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 -- mcp-reference
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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.
v2.0.11
33 findings · 14.4s
v0.3.74
22 findings · 6.9s
v0.1.0
0 findings · 4.9s
v0.1.0
2 findings · 4.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.4s
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 ·n/a: not applicablecisco-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 57 findings across every scanner that examined this package. None of the 3 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 14 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.
17 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_unicode_steganography, AAK-MCP-005, AAK-MCP-ATTEST-001 and 4 more · Files: /repo/mcp-use/docs/images/hero-dark.png, mcp-use/examples/airbnb_mcp.json, /repo/mcp-use/.github/SKILL.md and 4 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
7 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: RESOURCE_ABUSE_INFINITE_LOOP, AAK-MCP-HTTP-NOAUTH-SERVER-001, AAK-OAUTH-008 and 1 more · Files: /repo/mcp-use/tests/integration/servers_for_testing/custom_streaming_server.py, mcp-use/tests/integration/servers_for_testing/timeout_test_server.py, mcp-use/tests/integration/servers_for_testing/custom_streaming_server.py and 2 more · reported by cisco-skill-scanner, agent-audit-kit
2 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: MANIFEST_INVALID_NAME · Files: /repo/mcp-use/.github/ISSUE_TEMPLATE/SKILL.md, /repo/mcp-use/.github/SKILL.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
6 AAK-SECRET-004
Files: python/chat.py, mcp-use/mcp_use/observability/langfuse.py, mcp-use/mcp_use/observability/laminar.py and 1 more · reported by agent-audit-kit
2 AAK-DNS-REBIND-001
Files: mcp-use/mcp_use/task_managers/__init__.py, mcp-use/mcp_use/task_managers/streamable_http.py · reported by agent-audit-kit
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/mcp-use/mcp_use/connectors/sandbox.py · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/mcp-use/. · reported by cisco-skill-scanner
1 AAK-MCP-ATTEST-001
Files: mcp-server-config.json · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: pyproject.toml · reported by agent-audit-kit
8 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SECRET-001, TOOL_ABUSE_UNDECLARED_NETWORK, AAK-SEC-MD-001 and 2 more · Files: mcp-use/.env.example, /repo/repo/README.md, /repo/mcp-use/repo/mcp-use/CHANGELOG.md and 4 more · reported by agent-audit-kit, cisco-skill-scanner
6 The model did not answer for these findings.
Rules: AAK-DNS-REBIND-002, YARA_prompt_injection_unicode_steganography, SOCIAL_ENG_VAGUE_DESCRIPTION · Files: pyproject.toml, /repo/mcp-use/docs/images/hero-dark.png, /repo/SKILL.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner
Critical secrets exposure and DNS rebinding risks.
The artifact contains critical findings including potential secret exposure in `mcp-use/.env.example` and DNS rebinding vulnerabilities in `mcp-use/mcp_use/task_managers/__init__.py` and `mcp-use/mcp_use/task_managers/streamable_http.py`. High severity findings also point to secret exposure in telemetry and observability components, and a known SDK vulnerability. These issues, combined with observed network egress capabilities, warrant immediate attention.
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-SSRF-001
Files: mcp-use/mcp_use/connectors/sandbox.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit