Dominion Observatory MCP Server

Static scanners read the code. We measure what the MCP server actually does.

Dominion Observatory is the neutral, behavioral trust layer for Model Context Protocol servers — runtime reliability (uptime, success rate, latency) from real agent traffic, not a one-time code scan. Honest by design: unmeasured servers show as unrated, never a fake score. We are not a marketplace, so we can rate what others can't. Look up any server free.

Check a Server Free Agent Signup (auth.md) Add to Claude / Cursor Browse 22,561 Servers

22,561

Servers Indexed

Signed

Audit-Ready Reports

CI-Ready

API + Webhooks

For AI agents

Your agent can sign itself up. No human, no browser.

Dominion implements auth.md, the open agent-registration protocol from WorkOS. An agent discovers us, claims its own key, and verifies any MCP server before it connects — in one call.

:: 1. claim a key (no human in the loop) curl -X POST https://dominionobservatory.com/agent/auth -d '{"type":"anonymous"}'

:: 2. verify a server before calling it curl https://dominionobservatory.com/agent-query/ -H "Authorization: Bearer "

auth.md spec → agent onboarding skill →

Gate risky MCP servers in CI — fail the build below your trust threshold

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 22,561 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 22,561 servers.

📋

Compliance Attestation

Machine-readable attestation receipts for EU AI Act Article 12 and MiCA compliance. Audit-ready from day one.

🌐

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.

LangChainpip install langchain-mcp-trust-gate

CrewAIpip install crewai-dominion-trust

OpenAI Agentspip install openai-agents-trust-gate

Any MCP clientpip install dominion-observatory-sdk

Pricing

Scan one server free. Pay when MCP trust becomes part of how your team ships.

Free

$0

• Scan any server on demand
• Trust score + SLA grade
• Public report page
• No signup required Scan a server

Team / CI Most popular

$0.01 /query

• Unlimited scans via API
• Gate builds on a trust threshold
• Latency percentiles + history
• Monitoring & score-change alerts Get an API key

Compliance

$0.10 /query

• Everything in Team / CI
• Signed, audit-ready attestations
• EU AI Act Art. 12 & MiCA receipts
• Vendor-risk & audit-trail exports Talk to us

Run a registry, gateway, or marketplace? License the trust feed and show a trust score on every server you list.

Find out if your MCP servers are safe

Scan your first server free — no signup. Add it to CI when you're ready.

Scan a Server Free