Foxhound provides structured tracing, automated evaluation, cost controls, and compliance tooling for AI agent systems. The MCP server exposes 37 debugging tools for Claude Code, Cursor, Windsurf, and other MCP clients to query and analyze agent traces in real time. Users connect with an API key from foxhound.dev and the server integrates with both self-hosted and managed Foxhound deployments.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.