ucd-mcp

Behavioral trust scoring and MCP gateway proxy for 14,820+ MCP servers. Query real attestation data — interaction history, success rates, latency, uptime — before your agent executes sensitive operations. **8 tools** for trust evaluation, server discovery, and health monitoring: - `get-trust-score` — instant trust score (0-100) for any MCP server - `query-server` — full behavioral profile with attestation evidence - `list-servers` — browse the entire 14,820+ server directory - `get-leaderboard` — top-ranked servers by trust score - `check-health` — real-time uptime and latency checks - `get-compliance-report` — MiCA Article 12 compliance attestation receipts - `report-outcome` — report tool call outcomes to improve trust data - `get-baselines` — historical behavioral baselines **MCP Gateway Proxy**: Route agent calls through Observatory for automatic trust verification and compliance attestation. Every proxied call gets a trust check + signed attestation receipt. **Use cases**: Agent-to-agent commerce trust verification, MiCA Article 12 compliance (EU enforcement July 1, 2026), pre-flight trust checks before sensitive operations, continuous behavioral monitoring. Published spec: CTEF v0.3.2 (Zenodo DOI: 10.5281/zenodo.20285663)

Search your knowledge bases from any AI assistant using hybrid RAG.

Charter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans.

Create and manage cinematic AI video renders through the Future Video Studio Agent API.

Query trust scores for MCP servers and agent skills. Check if a tool is safe.

Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.