# dominion-observatory MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-vdineshk-dominion-observatory
- Repository: https://github.com/vdineshk/dominion-observatory

## Install
- Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://dominion-observatory.sgdata.workers.dev/mcp

## Tools
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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? Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp
- 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. Endpoint: https://dominion-observatory.sgdata.workers.dev/mcp

## Resources
- observatory://stats - Current network-wide statistics including total servers tracked, interactions recorded, and category breakdown. MIME type: application/json
- observatory://leaderboard - Top-rated MCP servers across all categories, ranked by trust score. MIME type: application/json

## Prompts
- assess_server_trust - Check trust score and reliability of an MCP server before using it. Provide the server URL and get a full trust assessment including score, latency, success rate, and recommendation. Arguments: server_url
- ecosystem_overview - Get a high-level overview of the MCP server ecosystem — how many servers are tracked, top categories, and the current state of behavioral baselines.

## Metadata
- Owner: io.github.vdineshk
- Version: 1.1.0
- Runtime: Sse
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 10, 2026
- Source: https://registry.modelcontextprotocol.io
