Visual testing tool for MCP servers
- vulnerabilities attested + 50
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 8
attested inferred mixed
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 6d ago · see ecosystem CVEs →
- C · 54 → E · 89
- C · 42 → C · 54
- D · 77 → C · 42
- B · 27 → D · 77
- high dangerous code
obfuscated payload: dynamic require()/import()
analyzed commit 795b1bb · analyzer v33 · 7h ago
skills & prompt files 12
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/board-ops/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/issue-create/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/issue-triage/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/local-dev/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/pr-flow/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/pre-push-gate/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/project-structure/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/release/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/test-servers/SKILL.md
- skill modelcontextprotocol-inspector-795b1bb/.claude/skills/testing/SKILL.md
- agent-rules modelcontextprotocol-inspector-795b1bb/AGENTS.md
- agent-rules modelcontextprotocol-inspector-795b1bb/CLAUDE.md
[](https://mcpobservatory.com/servers/github:modelcontextprotocol/inspector/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 modelcontextprotocol.