dominion-observatory
A trust scoring layer for the MCP ecosystem that lets agents verify server reliability before executing sensitive calls. You get 8 tools: check_trust returns 0-100 scores based on real interaction data, report_interaction feeds the collective intelligence loop, get_leaderboard surfaces top servers by category, and check_anomaly flags behavioral outliers. The gateway proxy mode automatically attaches trust checks and signed attestation receipts to every routed call, which matters for MiCA Article 12 compliance coming July 2026. Runs on Cloudflare Workers with a D1 database tracking 14,820+ servers. Reach for this when you need pre-flight verification before your agent touches unfamiliar infrastructure or when you want compliance attestation for regulated operations.
- tools
- 14
- transport
- HTTP
- last updated
- Apr 8, 2026
Tools
14 toolsPublic tool metadata for what this MCP can expose to an agent.
check_trustGet 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 agents have used it. Scores above 70 indicate reliable serve...
Get 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 agents have used it. Scores above 70 indicate reliable serve...
No parameter schema in public metadata yet.
clawhub_skill_trustCheck the supply-chain trust of a ClawHub (OpenClaw) skill BEFORE installing or invoking it. Returns a PASS/UNCERTAIN/FAIL badge and 0-100 score aggregating ClawHub's published security scan, moderation verdict, and provenance.
Check the supply-chain trust of a ClawHub (OpenClaw) skill BEFORE installing or invoking it. Returns a PASS/UNCERTAIN/FAIL badge and 0-100 score aggregating ClawHub's published security scan, moderation verdict, and provenance.
No parameter schema in public metadata yet.
verify_before_callRun a signed pre-invocation verification immediately before an agent sends money, credentials, private data, or write access to an MCP server. Returns PASS/UNCERTAIN/FAIL/UNRATED, evidence freshness, recommendation, and a signed diligence receipt.
Run a signed pre-invocation verification immediately before an agent sends money, credentials, private data, or write access to an MCP server. Returns PASS/UNCERTAIN/FAIL/UNRATED, evidence freshness, recommendation, and a signed diligence receipt.
No parameter schema in public metadata yet.
paid_trust_verdictGet the PREMIUM behavioral trust verdict for an MCP server, with a signed, citable, tamper-evident attestation receipt. This is a paid x402 service.
Get the PREMIUM behavioral trust verdict for an MCP server, with a signed, citable, tamper-evident attestation receipt. This is a paid x402 service.
No parameter schema in public metadata yet.
verify_attestationCryptographically 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.
Cryptographically 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 parameter schema in public metadata yet.
preflight_checkRun 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.
Run 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.
No parameter schema in public metadata yet.
report_interactionReport the outcome of calling an MCP server. Call this AFTER you use any MCP server to contribute to the trust network. This is free and takes <1ms.
Report the outcome of calling an MCP server. Call this AFTER you use any MCP server to contribute to the trust network. This is free and takes <1ms.
No parameter schema in public metadata yet.
get_leaderboardGet the top-rated MCP servers, optionally filtered by category. Use this to discover the most reliable MCP servers in the ecosystem.
Get the top-rated MCP servers, optionally filtered by category. Use this to discover the most reliable MCP servers in the ecosystem.
No parameter schema in public metadata yet.
get_baselinesGet behavioral baselines for a tool category. Shows what 'normal' looks like — average latency, success rates, typical call patterns.
Get behavioral baselines for a tool category. Shows what 'normal' looks like — average latency, success rates, typical call patterns.
No parameter schema in public metadata yet.
check_anomalyCheck if observed behavior from an MCP server is anomalous compared to baselines. Returns whether the behavior deviates significantly from normal patterns.
Check if observed behavior from an MCP server is anomalous compared to baselines. Returns whether the behavior deviates significantly from normal patterns.
No parameter schema in public metadata yet.
register_serverRegister a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
Register a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
No parameter schema in public metadata yet.
get_server_historyGet daily trust score and performance history for a server over the last 30 days.
Get daily trust score and performance history for a server over the last 30 days.
No parameter schema in public metadata yet.
observatory_statsGet overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and data freshness.
Get overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and data freshness.
No parameter schema in public metadata yet.
get_compliance_reportExport 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.
Export 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.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Dominion Observatory
The behavioral trust layer for the AI agent economy.
Check MCP server reliability before you call. Report outcomes to strengthen the trust network.
🌐 Live: https://dominionobservatory.com 📡 MCP Endpoint: https://dominionobservatory.com/mcp
What is this?
Every AI agent needs to know: "Can I trust this MCP server?" The Dominion Observatory answers that question with real runtime data — not GitHub stars, not static scans, but actual performance metrics from real agent interactions.
- Before calling an unknown MCP server →
check_trusttells you if it's reliable - After calling any MCP server →
report_interactioncontributes to the trust network - Every report makes scores better for everyone — this is a collective intelligence system
Tools (14)
Details
- Repository
- github.com/vdineshk/dominion-observatory
- Website
- dominion-observatory.sgdata.workers.dev
- Categories
- AI & LLM Tools, Monitoring & Observability, Data & Analytics, Finance & Commerce
- Transport
- HTTP
More from vdineshk
Related AI & LLM Tools MCP servers
View all
Ragoravelarynai/ragora-mcpSearch your knowledge bases from any AI assistant using hybrid RAG.0stars
Future Video Studioariadne-coil/fvs-mcpCreate and manage cinematic AI video renders through the Future Video Studio Agent API.0stars
Voidfeed Mcpvoidfeedai-ops/voidfeed-mcpKnowledge API for AI agents — content, agent directory, model benchmarks, semantic search.0stars
RegexForgewalkojas-boop/regexforgeDeterministic regex synthesis from labeled examples. Zero LLM, proof matrix, backtracking audit.0stars
Withvibe Voterwithvibe/withvibe-voterVote-gated change control for WithVibe — the agent proposes a change via MCP; team approves first.0stars
Wish Gameworld.3keys/wish-gameWish game — every agent wish permanently reshapes a shared world. Free, no key needed.0stars