Dominion Observatory MCP Server

The io.github.vdineshk/dominion-observatory server provides a runtime behavioral trust scoring layer for MCP servers. It checks reliability using real performance outcomes from agent interactions rather than static indicators, and reports results to strengthen a trust network.

🛠️ Key Features

Runtime behavioral trust scoring for MCP servers
Reliability checks before calling unknown tools
Reporting of outcomes to the trust network
Published live endpoint and MCP endpoint (per readme excerpt)

🚀 Use Cases

Determine whether an MCP server is reliable before invoking it
Improve trust decisions by using runtime performance metrics

⚡ Developer Benefits

Reduce risk from calling unknown MCP tools by validating reliability first
Use reported outcome data as a basis for trust scoring

⚠️ Limitations

The provided excerpt does not describe specific tooling, scoring methodology details, or supported operations beyond the reliability check and outcome reporting.

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_trust tells you if it's reliable

After calling any MCP server → report_interaction contributes 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

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)

bash

# 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.

Install

Remote endpoint

SSE

Hosted server - connect over the network, no local install.

url

https://dominion-observatory.sgdata.workers.dev/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "dominion-observatory": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://dominion-observatory.sgdata.workers.dev/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.vdineshk/dominion-observatory

Dominion Observatory MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Dominion Observatory

What is this?

Tools (8)

Quick Start

For agents (MCP)

For developers (REST API)

How Trust Scores Work

Architecture

Data Collection

Categories

Operator

License

Install

Remote endpoint

Related servers