Dominion Observatory
vdineshk/dominion-observatory
Built to answer "can I trust this MCP server before I call it" with runtime behavioral data instead of static reputation signals. You get eight tools: check_trust for pre-call scoring, report_interaction to feed the collective dataset, get_leaderboard for top servers by category, and check_anomaly to flag weird behavior. Trust scores blend GitHub metadata with real success rates and latency from agent interactions. Runs on Cloudflare Workers with a D1 backend and exposes both MCP and REST endpoints. Reach for this when you're wiring up agents that call third-party MCP servers and need a trust layer that improves as more agents report outcomes. The behavioral dataset compounds daily, so early reporters strengthen the network for everyone.
- GitHub stars
- 1
- tools
- 10
- last updated
- Apr 10, 2026
Tools
10 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...1 params
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...
Parameters* required
server_urlstringThe URL of the MCP server to check (e.g., https://example.workers.dev/mcp)
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.7 params
Report 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.
Parameters* required
error_messagestringIf failed: brief error description
error_typestringIf failed: timeout, auth_error, invalid_response, server_error, rate_limited, schema_mismatch
http_statusintegerHTTP status code returned (200, 429, 500, etc.)
latency_msnumberHow long the call took in milliseconds
server_urlstringThe URL of the MCP server you called
successbooleanDid the call succeed? true = worked as expected, false = error or unexpected result
tool_namestringWhich tool you called on the server
get_leaderboardGet 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, productivity, communication.2 params
Get 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, productivity, communication.
Parameters* required
categorystringFilter by category (optional). Leave empty for overall leaderboard.
limitintegerNumber of results (default 10, max 50)
get_baselinesGet 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 for its category.1 params
Get 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 for its category.
Parameters* required
categorystringThe tool category to get baselines for (e.g., weather, finance, code, data)
check_anomalyCheck 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 normal patterns.3 params
Check 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 normal patterns.
Parameters* required
observed_latency_msnumberThe latency you observed
observed_success_ratenumberSuccess rate you've observed (0.0 to 1.0)
server_urlstringThe MCP server URL to check
register_serverRegister a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.5 params
Register a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
Parameters* required
categorystringPrimary category: weather, finance, code, data, search, compliance, transport, productivity, communication, other
descriptionstringWhat the server does
github_urlstringGitHub repository URL (optional, improves static score)
namestringHuman-readable name of the server
server_urlstringThe MCP server URL
get_server_historyGet 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?1 params
Get 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?
Parameters* required
server_urlstringThe MCP server URL
observatory_statsGet 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 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.
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. Essential for enterprises that need to prove their AI agents are behaving correctly.4 params
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. Essential for enterprises that need to prove their AI agents are behaving correctly.
Parameters* required
agent_idstringFilter by agent ID (optional)
end_datestringEnd date in YYYY-MM-DD format (optional)
server_urlstringFilter by server URL (optional)
start_datestringStart date in YYYY-MM-DD format (optional)
get_mica_attestationGenerate a MiCA / EU AI Act Article 12 compliance attestation for an MCP server. CRITICAL after July 1, 2026: the EU MiCA transitional period expires and agents operating in EU-regulated contexts need auditable behavioral attestation. Returns compliance grade, risk level, moni...1 params
Generate a MiCA / EU AI Act Article 12 compliance attestation for an MCP server. CRITICAL after July 1, 2026: the EU MiCA transitional period expires and agents operating in EU-regulated contexts need auditable behavioral attestation. Returns compliance grade, risk level, moni...
Parameters* required
server_urlstringThe MCP server URL to generate attestation for
Sponsors
Readme
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)
| Tool | Description |
|---|---|
check_trust | 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 servers. Scores below 30 indicate risky servers. |
clawhub_skill_trust | Check 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 0-100 score aggregating ClawHub's published security scan (VirusTotal + model), moderation verdict, and provenance. Malicious/suspicious/blocked => FAIL; unscanned => UNCERTAIN. |
verify_before_call | Run 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 MCP HTTP request with Authorization: Bearer do_<api_key> for Stripe metering ($0.01/call), or call once without payment to receive x402 instructions and retry with payment_tx. Returns PASS/UNCERTAIN/FAIL/UNRATED, evidence freshness, recommendation, and a signed diligence receipt. |
paid_trust_verdict | Get 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 Base), pay, then call again WITH the payment_tx (transaction hash, single-use) to receive the full verdict + receipt. The free check_trust tool remains available for basic scores. |
verify_attestation | 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 trust in this server required). Use this to confirm a receipt another party gave you is authentic and untampered. |
preflight_check | 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 you keep as proof you performed a trust check — the standard of care after the ClawHavoc/Miasma supply-chain attacks. Call this before connecting to or invoking any unfamiliar MCP server. |
report_interaction | Report 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 | Get 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, productivity, communication. |
get_baselines | Get 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 for its category. |
check_anomaly | Check 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 normal patterns. |
register_server | Register 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 | Get 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 | Get 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 | 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. Essential for enterprises that need to prove their AI agents are behaving correctly. |
Quick Start
For agents (MCP)
Connect to: https://dominionobservatory.com/mcp
For developers (REST API)
# Check trust score
curl "https://dominionobservatory.com/api/trust?url=https://example.workers.dev/mcp"
# View leaderboard
curl "https://dominionobservatory.com/api/leaderboard"
# Network stats
curl "https://dominionobservatory.com/api/stats"
How Trust Scores Work
Trust scores range from 0-100 and combine two signals:
- Static score (30%): GitHub presence, documentation quality, authentication support
- Runtime score (70%): Real success rates, latency, error patterns from agent interactions
Scores above 70 = reliable. Below 30 = risky. The more agents report interactions, the more accurate scores become.
Architecture
- Runtime: Cloudflare Workers (330+ global edge locations, <1ms cold start)
- Database: Cloudflare D1 (SQLite at the edge)
- Protocol: MCP (Model Context Protocol) + REST API
- Cost: Runs on free tier
Data Collection
Started: April 8, 2026
Every interaction reported to the observatory strengthens the trust network for all agents. The behavioral dataset compounds daily — it cannot be replicated by competitors who start later.
Categories
weather · finance · code · data · search · compliance · transport · productivity · communication
Operator
Built by Dinesh Kumar in Singapore. Part of the Dominion Agent Economy Engine (DAEE).
License
MIT
Details
- Repository
- github.com/vdineshk/dominion-observatory
- Transport
- SSE
- Registry
- MCP registry, active