Observatory

com.dominionobservatory由 dominionobservatory.com 發布官方發布者v1.2.0更新於 Oct 30, 2026

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

已驗證Streamable HTTP可網頁執行開發者工具安全與監控

概覽

AI 產生的概覽

遠端 MCP 服務，為其他 MCP 伺服器與技能提供執行期行為信任評分，讓助理在呼叫未知工具前先評估可靠性。

可以做什麼
  • 查詢 MCP 伺服器的信任分數、延遲、上線率與成功率，並檢視 30 天歷史與依類別基準的異常偵測
  • 在向伺服器送出金錢、憑證或寫入權限前執行預檢與簽章驗證，並核驗 Dominion 簽署的證明
  • 在安裝或呼叫 ClawHub 技能前檢查其供應鏈信任狀況
  • 回報互動結果以充實共享信任網路
  • 檢視排行榜、類別基準與網路整體統計
  • 匯出可供合規稽核的互動紀錄
適用情境
當助理即將連線或呼叫不熟悉的 MCP 伺服器或第三方技能，需要執行期可靠性訊號、簽署的盡職調查憑證，或需要代理互動的合規稽核紀錄時適用。
執行需求
遠端 streamable HTTP 端點；未宣告本機套件、環境變數或請求標頭。部分工具需付費：verify_before_call 在三次免費驗證後須以 Authorization Bearer API 金鑰驗證，paid_trust_verdict 須提供鏈上支付交易雜湊。
安裝前請注意
多項工具涉及付費：verify_before_call 免費額度後按次計費，paid_trust_verdict 須在 Base 上以加密貨幣付款。回報互動會把呼叫資料傳送給第三方，合規報告會匯出互動紀錄。信任分數屬第三方評級，並非可靠性保證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Observatory，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.dominionobservatory%2Fobservatory/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "observatory": {
      "type": "http",
      "url": "https://dominionobservatory.com/mcp"
    }
  }
}

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_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 (14)

ToolDescription
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 servers. Scores below 30 indicate risky servers.
clawhub_skill_trustCheck 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_callRun 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_verdictGet 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_attestationCryptographically 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_checkRun 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_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.
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.
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.
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.
register_serverRegister a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
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?
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_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.

Quick Start

For agents (MCP)

Connect to: https://dominionobservatory.com/mcp

For developers (REST API)

bash
# Check trust scorecurl "https://dominionobservatory.com/api/trust?url=https://example.workers.dev/mcp"
# View leaderboardcurl "https://dominionobservatory.com/api/leaderboard"
# Network statscurl "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

來源：README.md，提交 57fdc72

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

2
  1. v1.2.0最新Oct 9, 2026
  2. v1.0.0Sep 16, 2026

評分

已滿足適用檢查項的 75%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Dominionobservatory 整合

Dominion Observatory

由 GitHub 帳號 vdineshk 發布

遠端信任評分服務，讓助理查詢 MCP 伺服器的可靠性、驗證簽章證明，並回報呼叫結果。

SSE可網頁執行
開發者工具尚未收錄Oct 25, 2026

Ai Compliance Monitor

由 GitHub 帳號 vdineshk 發布

提供 AI 代理跨司法管轄區的法規情報，讓助理查詢合規義務、條文、期限與跨國比較。

Streamable HTTP可網頁執行
知識與記憶4 個工具Oct 24, 2026