Summary
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.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
10 tools
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
successbooleanDid the call succeed? true = worked as expected, false = error or unexpected result
tool_namestringWhich tool you called on the server
error_typestringIf failed: timeout, auth_error, invalid_response, server_error, rate_limited, schema_mismatch
latency_msnumberHow long the call took in milliseconds
server_urlstringThe URL of the MCP server you called
http_statusintegerHTTP status code returned (200, 429, 500, etc.)
error_messagestringIf failed: brief error description
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
limitintegerNumber of results (default 10, max 50)
categorystringFilter by category (optional). Leave empty for overall leaderboard.
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
server_urlstringThe MCP server URL to check
observed_latency_msnumberThe latency you observed
observed_success_ratenumberSuccess rate you've observed (0.0 to 1.0)
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
namestringHuman-readable name of the server
categorystringPrimary category: weather, finance, code, data, search, compliance, transport, productivity, communication, other
github_urlstringGitHub repository URL (optional, improves static score)
server_urlstringThe MCP server URL
descriptionstringWhat the server does
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
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://dominion-observatory.sgdata.workers.dev 📡 MCP Endpoint: https://dominion-observatory.sgdata.workers.dev/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 (8)
| Tool | Description |
|---|---|
check_trust | Get trust score and reliability metrics for any MCP server |
report_interaction | Report success/failure after calling an MCP server |
get_leaderboard | Top-rated MCP servers by category |
get_baselines | Behavioral baselines for a tool category |
check_anomaly | Is this server behavior normal or anomalous? |
register_server | Register a new MCP server (free) |
get_server_history | 30-day trust score trend for a server |
observatory_stats | Overall network statistics |
Quick Start
For agents (MCP)
Connect to: https://dominion-observatory.sgdata.workers.dev/mcp
For developers (REST API)
# Check trust score
curl "https://dominion-observatory.sgdata.workers.dev/api/trust?url=https://example.workers.dev/mcp"
# View leaderboard
curl "https://dominion-observatory.sgdata.workers.dev/api/leaderboard"
# Network stats
curl "https://dominion-observatory.sgdata.workers.dev/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
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →