com.dominionobservatory/observatory

by dominionobservatory.com · remote · no sign-in to list tools · v1.2.0 · published by com.dominionobservatory

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

Changes · 7

Compare Registry entry

14 tools: 7 change things and 7 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things7Claude Code: ask: see these tools
Only reads7Claude Code: allow: see these tools

4 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http observatory https://dominionobservatory.com/mcp

Findings

Matches of fixed checks, with the text they matched.

2 warn2 info

Warnverify_before_call
The server marks "verify_before_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true}; The name "verify_before_call" says "call": a word for a change.
What this check looks for
Warnpreflight_check
The server marks "preflight_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true}; The description's first verb is "run": a word for a change.
What this check looks for
Infoverify_before_call
The description mentions "credentials".
Matched text
description: "...mmediately before an agent sends money, credentials, private data, or write access to an MC..."
What this check looks for
Infoverify_before_call
The input schema at properties.reason.description mentions "credentials".
Matched text
inputSchema.properties.reason.description: "...al reason for verification, e.g. money, credentials, private_data, write_access"
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

14 tools

Changes things 7Creates or changes something that can be changed back.Claude Code: ask

check_anomalyCheck if observed behavior from an MCP server is anomalous compared to baselines.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- title: Check Anomaly
- readOnlyHint: true
clawhub_skill_trustCheck the supply-chain trust of a ClawHub (OpenClaw) skill BEFORE installing or invoking it.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Check 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.
Annotations the server declares
- title: Check ClawHub Skill Trust
- readOnlyHint: true
preflight_checkRun a PRE-FLIGHT due-diligence check on an MCP server BEFORE your agent invokes it.1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "preflight_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true}; The description's first verb is "run": a word for a change.
  What this check looks for
Description, as the server wrote it
Run 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.
Annotations the server declares
- title: Pre-flight Diligence Check
- readOnlyHint: true
register_serverRegister a new MCP server in the observatory.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
Register a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.
Annotations the server declares
- title: Register Server
- destructiveHint: false
report_interactionReport the outcome of calling an MCP server.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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.
Annotations the server declares
- title: Report Interaction
- destructiveHint: false
verify_attestationCryptographically verify a Dominion signed attestation (JWS) — e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Cryptographically 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.
Annotations the server declares
- title: Verify Attestation
- readOnlyHint: true
verify_before_callRun a signed pre-invocation verification immediately before an agent sends money, credentials, private data, or write access to an MCP server.3 findings
Why it is in this group
- The name "verify_before_call" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
  The description mentions "credentials".
  Matched text
  description: "...mmediately before an agent sends money, credentials, private data, or write access to an MC..."
  What this check looks for
- Info
  The input schema at properties.reason.description mentions "credentials".
  Matched text
  inputSchema.properties.reason.description: "...al reason for verification, e.g. money, credentials, private_data, write_access"
  What this check looks for
- Warn
  The server marks "verify_before_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true}; The name "verify_before_call" says "call": a word for a change.
  What this check looks for
Description, as the server wrote it
Run 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.
Annotations the server declares
- title: Verify Before Consequential Call
- readOnlyHint: true

Only reads 7Looks things up and changes nothing.Claude Code: allow

check_trustGet the trust score and reliability metrics for any MCP server.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Check Trust Score
- readOnlyHint: true
get_baselinesGet behavioral baselines for a tool category.No findings
Why it is in this group
- The name "get_baselines" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Get Baselines
- readOnlyHint: true
get_compliance_reportExport a compliance-ready audit trail of all recorded interactions.No findings
Why it is in this group
- The name "get_compliance_report" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Get Compliance Report
- readOnlyHint: true
get_leaderboardGet the top-rated MCP servers, optionally filtered by category.No findings
Why it is in this group
- The name "get_leaderboard" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Get Leaderboard
- readOnlyHint: true
get_server_historyGet daily trust score and performance history for a server over the last 30 days.No findings
Why it is in this group
- The name "get_server_history" says "get": a word for reading.
Description, as the server wrote it
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?
Annotations the server declares
- title: Get Server History
- readOnlyHint: true
observatory_statsGet overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and data freshness.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Observatory Stats
- readOnlyHint: true
paid_trust_verdictGet the PREMIUM behavioral trust verdict for an MCP server, with a signed, citable, tamper-evident attestation receipt.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it
Get 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.
Annotations the server declares
- title: Paid Trust Verdict (x402)
- readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http observatory https://dominionobservatory.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__observatory__check_trust",
      "mcp__observatory__paid_trust_verdict",
      "mcp__observatory__get_leaderboard",
      "mcp__observatory__get_baselines",
      "mcp__observatory__get_server_history",
      "mcp__observatory__observatory_stats",
      "mcp__observatory__get_compliance_report"
    ],
    "ask": [
      "mcp__observatory__clawhub_skill_trust",
      "mcp__observatory__verify_before_call",
      "mcp__observatory__verify_attestation",
      "mcp__observatory__preflight_check",
      "mcp__observatory__report_interaction",
      "mcp__observatory__check_anomaly",
      "mcp__observatory__register_server"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as observatory. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.dominionobservatory/observatory/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

7 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:54 UTC.

For agents: Markdown · JSON · report this listing