Free scanners rate a server once — then a silently updated tool description turns your agent against you (the attack Microsoft warned every Copilot customer about, June 2026). Independent research across 9,695 MCP servers found popularity and verification badges don't predict security. Dominion is the continuous layer: we baseline your server's tool manifest, re-verify it every ~20 minutes, alert you the moment anything drifts, and sign the attestation trail your compliance review needs. Honest by design: servers without runtime data show as unrated, never a fake score.
# In your CI pipeline, before an MCP server is approved: score=$(curl -s "https://dominionobservatory.com/api/trust?url=$MCP_URL" | jq .trust_score) if [ "$score" -lt 70 ]; then echo "Blocked: $MCP_URL trust score $score is below policy (70)" exit 1 fi # Compliance tier returns a signed, audit-ready attestation: curl "https://dominionobservatory.com/api/trust/verascore?subject=$MCP_URL"
If your company is adopting MCP, someone has to answer "can we trust this server?" Observatory is that answer — backed by behavioral data on 47,544 servers and signed so it holds up in an audit.
Every call gets a trust score based on real behavioral data: success rates, latency patterns, anomaly detection across 47,544 servers.
Tamper-evident, machine-readable runtime records designed to support audit evidence, internal governance, and applicable record-keeping assessments. Legal compliance depends on your organisation, system classification, and deployment context — a Dominion receipt alone does not establish compliance.
Route any MCP server through Observatory. Trust checks happen transparently. No code changes needed — just change the URL.
Cross-ecosystem reliability baselines built from agent-reported telemetry. Data that ages into compounding value.
Agent Information Optimization — check any MCP server's discoverability to AI agents. Scores llms.txt, agent.json, registry presence, and more. Try it free →
Scan your first server free. CI/monitoring plans for platform teams, and a Compliance tier with signed attestations for audit and vendor-risk reviews. See pricing →
Install a package. Add one line. Trust checks are automatic.
pip install langchain-mcp-trust-gatepip install crewai-dominion-trustpip install openai-agents-trust-gatepip install dominion-observatory-sdkTrust scores that moved in the last 72 hours
Scan one server free. Pay when MCP trust becomes part of how your team ships.
A signed, dated, independently-verifiable trust badge for your README — $29 one-time, self-serve, no sales call.
Get verified — $29 →Run a registry, gateway, or marketplace? License the trust feed and show a trust score on every server you list.
Scan your first server free — no signup. Add it to CI when you're ready.
Scan a Server Free