Agents Index

Observatory

Online

Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.

Visit publisherConnectJSON

What it can do: 14 tools

  • check_trust read-onlyGet the trust score and reliability metrics for any MCP server. Use this BEFORE calling an unknown MCP server to assess if it's reliable. Returns trust_score (0-100), latency stats, uptime, success rate, and how many age
  • clawhub_skill_trust read-onlyCheck the supply-chain trust of a ClawHub (OpenClaw) skill BEFORE installing or invoking it. After the Feb-2026 ClawHavoc supply-chain attack, third-party skills can carry malware. Returns a PASS/UNCERTAIN/FAIL badge and
  • verify_before_call read-onlyRun a signed pre-invocation verification immediately before an agent sends money, credentials, private data, or write access to an MCP server. The first 3 verifications per agent are free. After that, authenticate the MC
  • paid_trust_verdict read-onlyGet the PREMIUM behavioral trust verdict for an MCP server, with a signed, citable, tamper-evident attestation receipt. This is a paid x402 service: call WITHOUT payment_tx to receive payment instructions (0.001 USDC on
  • verify_attestation read-onlyCryptographically verify a Dominion signed attestation (JWS) — e.g. a trust-verdict receipt, gateway attestation, or MCP Verified badge. Stateless: checks the Ed25519 signature against Dominion's published public key (no
  • preflight_check read-onlyRun a PRE-FLIGHT due-diligence check on an MCP server BEFORE your agent invokes it. Returns a verdict (PASS/UNCERTAIN/FAIL/UNRATED) plus a SIGNED, timestamped diligence receipt you keep as proof you performed a trust che
  • report_interactionReport the outcome of calling an MCP server. Call this AFTER you use any MCP server to contribute to the trust network. Your report helps other agents make better decisions. This is free and takes <1ms.
  • get_leaderboard read-onlyGet the top-rated MCP servers, optionally filtered by category. Use this to discover the most reliable MCP servers in the ecosystem. Categories include: weather, finance, code, data, search, compliance, transport, produc
  • get_baselines read-onlyGet behavioral baselines for a tool category. Shows what 'normal' looks like — average latency, success rates, typical call patterns. Use this to evaluate whether a specific server's performance is within normal range fo
  • check_anomaly read-onlyCheck if observed behavior from an MCP server is anomalous compared to baselines. Use this when a server seems slow, unreliable, or returns unexpected results. Returns whether the behavior deviates significantly from nor
  • register_serverRegister a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
  • get_server_history read-onlyGet daily trust score and performance history for a server over the last 30 days. Use this to see trends — is the server improving or degrading?
  • observatory_stats read-onlyGet overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and data freshness. Use this to understand the scope of the trust network.
  • get_compliance_report read-onlyExport a compliance-ready audit trail of all recorded interactions. Formatted for EU AI Act Article 12 and Singapore IMDA Agentic AI Governance Framework. Filter by server, agent, or date range. Essential for enterprises

Connect it

Claude Code
claude mcp add --transport http observatory https://dominionobservatory.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://dominionobservatory.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "observatory": {
      "url": "https://dominionobservatory.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "observatory": {
      "type": "http",
      "url": "https://dominionobservatory.com/mcp"
    }
  }
}

Questions

What does Observatory do?

Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools. It exposes 14 tools to AI assistants.

What tools does Observatory provide?

14 tools, including check_trust, clawhub_skill_trust, verify_before_call, paid_trust_verdict, verify_attestation, preflight_check, report_interaction, get_leaderboard, get_baselines, check_anomaly, register_server, get_server_history….

How do I connect Observatory to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://dominionobservatory.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Observatory require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Observatory online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Observatory?

dominionobservatory.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Analytics & BI