Hosted MCP server · #154 most used on Smithery

dominion-observatory

vdineshk/dominion-observatory

Behavioral trust scoring and MCP gateway proxy for 14,820+ MCP servers. Query real attestation data — interaction history, success rates, latency, uptime — before your agent executes sensitive operations. **8 tools** for trust evaluation, server discovery, and health monitoring: - `get-trust-score` — instant trust score (0-100) for any MCP server - `query-server` — full behavioral profile with attestation evidence - `list-servers` — browse the entire 14,820+ server directory - `get-leaderboard` — top-ranked servers by trust score - `check-health` — real-time uptime and latency checks - `get-compliance-report` — MiCA Article 12 compliance attestation receipts - `report-outcome` — report tool call outcomes to improve trust data - `get-baselines` — historical behavioral baselines **MCP Gateway Proxy**: Route agent calls through Observatory for automatic trust verification and compliance attestation. Every proxied call gets a trust check + signed attestation receipt. **Use cases**: Agent-to-agent commerce trust verification, MiCA Article 12 compliance (EU enforcement July 1, 2026), pre-flight trust checks before sensitive operations, continuous behavioral monitoring. Published spec: CTEF v0.3.2 (Zenodo DOI: 10.5281/zenodo.20285663)

Data & databases DevOps & cloud Agents & orchestration

Install ↓Smithery ↗Website ↗

Uses: 3.5k
Tools: 10
Runs: Hosted
Prompts: 2
Listed: 7mo ago

Get started

Add it to your agent

npx -y @smithery/cli@latest install vdineshk/dominion-observatory --client claude

Swap --client claude for cursor, vscode, windsurf or another client. The CLI asks for any required settings.

claude mcp add --transport http dominion-observatory https://server.smithery.ai/vdineshk/dominion-observatory/mcp

A hosted server: nothing to install. Run /mcp in Claude Code to sign in if it asks.

[mcp_servers.dominion-observatory]
url = "https://server.smithery.ai/vdineshk/dominion-observatory/mcp"

Add to ~/.codex/config.toml.

{
  "mcpServers": {
    "dominion-observatory": {
      "url": "https://server.smithery.ai/vdineshk/dominion-observatory/mcp"
    }
  }
}

Add to ~/.cursor/mcp.json.

{
  "servers": {
    "dominion-observatory": {
      "type": "http",
      "url": "https://server.smithery.ai/vdineshk/dominion-observatory/mcp"
    }
  }
}

Add to .vscode/mcp.json.

gemini mcp add --transport http dominion-observatory https://server.smithery.ai/vdineshk/dominion-observatory/mcp

Saved to .gemini/settings.json.

What it can do

10 tools

check_trust1 paramGet the trust score and reliability metrics for any MCP server. Use this BEFORE calling an unknown MCP server to assess if it's reliable.…

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.

Parameter	Type	Description
`server_url`	string	The URL of the MCP server to check (e.g., https://example.workers.dev/mcp)

report_interaction7 paramsReport the outcome of calling an MCP server. Call this AFTER you use any MCP server to contribute to the trust network. Your report helps…

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.

Parameter	Type	Description
`success`	boolean	Did the call succeed? true = worked as expected, false = error or unexpected result
`tool_name`	string	Which tool you called on the server
`error_type`	string	If failed: timeout, auth_error, invalid_response, server_error, rate_limited, schema_mismatch
`latency_ms`	number	How long the call took in milliseconds
`server_url`	string	The URL of the MCP server you called
`http_status`	integer	HTTP status code returned (200, 429, 500, etc.)
`error_message`	string	If failed: brief error description

get_leaderboard2 paramsGet the top-rated MCP servers, optionally filtered by category. Use this to discover the most reliable MCP servers in the ecosystem. Cate…

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.

Parameter	Type	Description
`limit`	integer	Number of results (default 10, max 50)
`category`	string	Filter by category (optional). Leave empty for overall leaderboard.

get_baselines1 paramGet behavioral baselines for a tool category. Shows what 'normal' looks like — average latency, success rates, typical call patterns. Use…

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.

Parameter	Type	Description
`category`	string	The tool category to get baselines for (e.g., weather, finance, code, data)

check_anomaly3 paramsCheck if observed behavior from an MCP server is anomalous compared to baselines. Use this when a server seems slow, unreliable, or retur…

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.

Parameter	Type	Description
`server_url`	string	The MCP server URL to check
`observed_latency_ms`	number	The latency you observed
`observed_success_rate`	number	Success rate you've observed (0.0 to 1.0)

register_server5 paramsRegister a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is f…

Register a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.

Parameter	Type	Description
`name`	string	Human-readable name of the server
`category`	string	Primary category: weather, finance, code, data, search, compliance, transport, productivity, communication, other
`github_url`	string	GitHub repository URL (optional, improves static score)
`server_url`	string	The MCP server URL
`description`	string	What the server does

get_server_history1 paramGet daily trust score and performance history for a server over the last 30 days. Use this to see trends — is the server improving or deg…

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?

Parameter	Type	Description
`server_url`	string	The MCP server URL

observatory_statsGet overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and dat…

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_report4 paramsExport a compliance-ready audit trail of all recorded interactions. Formatted for EU AI Act Article 12 and Singapore IMDA Agentic AI Gove…

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.

Parameter	Type	Description
`agent_id`	string	Filter by agent ID (optional)
`end_date`	string	End date in YYYY-MM-DD format (optional)
`server_url`	string	Filter by server URL (optional)
`start_date`	string	Start date in YYYY-MM-DD format (optional)

get_mica_attestation1 paramGenerate a MiCA / EU AI Act Article 12 compliance attestation for an MCP server. CRITICAL after July 1, 2026: the EU MiCA transitional pe…

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, monitoring continuity status, and links to full audit exports.

Parameter	Type	Description
`server_url`	string	The MCP server URL to generate attestation for

Ready-made

Prompts

assess_server_trustCheck 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.
ecosystem_overviewGet a high-level overview of the MCP server ecosystem — how many servers are tracked, top categories, and the current state of behavioral baselines.

Readable data

Resources

Observatory StatisticsCurrent network-wide statistics including total servers tracked, interactions recorded, and category breakdown.
Server LeaderboardTop-rated MCP servers across all categories, ranked by trust score.