Dominion Observatory
An observatory that probes every MCP server in the official MCP registry and reports which ones actually work: live, auth-gated, dead, or erroring.
Documentation
A scan is a snapshot. MCP servers change after you approve them.
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.
~20 min
Drift-Detection Cadence
Signed
Audit-Ready Attestations
47,544
Projects Indexed
# 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"
Why teams scan with Observatory
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.
🛡
Trust Verification
Every call gets a trust score based on real behavioral data: success rates, latency patterns, anomaly detection across 47,544 servers.
📋
Compliance Attestation
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.
🌐
Gateway Proxy
Route any MCP server through Observatory. Trust checks happen transparently. No code changes needed — just change the URL.
📊
Behavioral Baselines
Cross-ecosystem reliability baselines built from agent-reported telemetry. Data that ages into compounding value.
⚡
AIO Audit
Agent Information Optimization — check any MCP server's discoverability to AI agents. Scores llms.txt, agent.json, registry presence, and more. Try it free →
💳
Priced for teams, not experiments
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 →
Works with your stack
Install a package. Add one line. Trust checks are automatic.
LangChain pip install langchain-mcp-trust-gate
CrewAI pip install crewai-dominion-trust
OpenAI Agents pip install openai-agents-trust-gate
Any MCP client pip install dominion-observatory-sdk
Score Changes
Trust scores that moved in the last 72 hours
Pricing
Scan one server free. Pay when MCP trust becomes part of how your team ships.
$0.01 /query
- Unlimited scans via API
- Gate builds on a trust threshold
- Latency percentiles + history
- Monitoring & score-change alerts
Compliance
$0.10 /query
Built an MCP server? Get it MCP Verified ✓
A signed, dated, independently-verifiable trust badge for your README — $29 one-time, self-serve, no sales call.
Run a registry, gateway, or marketplace? License the trust feed and show a trust score on every server you list.