Security scanner for Model Context Protocol servers. Catch tool poisoning, prompt injection, and supply-chain attacks before your AI agent runs them.
- capability exposure inferred + 35
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- A · 0 → C · 35
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 3531afc · analyzer v33 · 1d ago
skills & prompt files 24
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/auth-hardening-auditor.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/ci-sarif-engineer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/detection-rule-engineer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/diff-snapshot-dev.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/docs-maintainer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/package-source-scanner.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/sandbox-runtime-engineer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/scoring-fp-engineer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/source-analysis-engineer.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/supply-chain-analyst.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/test-qa.md
- agent-rules yatuk-mcpradar-3531afc/.claude/agents/transport-specialist.md
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/auth-hardening-auditor.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/ci-sarif-engineer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/detection-rule-engineer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/diff-snapshot-dev.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/docs-maintainer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/package-source-scanner.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/sandbox-runtime-engineer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/scoring-fp-engineer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/source-analysis-engineer.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/supply-chain-analyst.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/test-qa.toml
- agent-rules yatuk-mcpradar-3531afc/.codex/agents/transport-specialist.toml
danger signals4
- suspicious endpoint 169.254.169.254 (cloud metadata) yatuk-mcpradar-3531afc/tests/test_javascript_analyzer.py :106
"fetch('http://169.254.169.254/latest');", - suspicious endpoint 169.254.169.254 (cloud metadata) yatuk-mcpradar-3531afc/tests/test_oauth_r112.py :154
json={"authorization_servers": ["http://169.254.169.254/latest"]}, - suspicious endpoint 169.254.169.254 (cloud metadata) yatuk-mcpradar-3531afc/tests/test_safe_http.py :28
"http://169.254.169.254/latest/meta-data", - suspicious endpoint 169.254.169.254 (cloud metadata) yatuk-mcpradar-3531afc/tests/test_source_analyzer.py :24
f = _scan("url = 'http://169.254.169.254/latest/meta-data/'\n", tmp_path)
[](https://mcpobservatory.com/servers/github:yatuk/mcpradar/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of yatuk.