MCP Radar
MCPサーバー

Dominion Observatory

com.dominionobservatory/observatory
MCP・エージェント基盤 セキュリティ 公開・接続可能 MCP 2026-07-28

このMCPでできること

Evaluates MCP server trust, reliability, behavioral anomalies, attestations, and compliance audit records.

機能

ツール

15 ツール
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_url'], 'properties': {'server_url': {'type': 'string', 'description': 'The MCP server URL to check'}, 'observed_latency_ms': {'type': 'number', 'description': 'The latency you observed'}, 'observed_success_rate': {'type': 'number', 'description': "Success rate you've observed (0.0 to 1.0)"}}}
出力スキーマ 
{'type': 'object', 'properties': {'anomalies': {'type': 'array', 'items': {'type': 'object', 'properties': {'detail': {'type': 'string', 'description': 'Human-readable explanation'}, 'metric': {'type': 'string', 'description': 'Which metric is anomalous (latency, success_rate)'}, 'severity': {'type': 'string', 'description': 'high or medium'}}}}, 'server_url': {'type': 'string'}, 'is_anomalous': {'type': 'boolean', 'description': 'Whether behavior is anomalous'}, 'recommendation': {'type': 'string'}, 'server_baselines': {'type': 'object', 'properties': {'success_rate': {'type': 'number'}, 'avg_latency_ms': {'type': 'number'}, 'total_data_points': {'type': 'integer'}}}}}
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_url'], 'properties': {'server_url': {'type': 'string', 'description': 'The URL of the MCP server to check (e.g., https://example.workers.dev/mcp)'}}}
出力スキーマ 
{'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'Server display name'}, 'found': {'type': 'boolean', 'description': 'Whether the server was found in the observatory'}, 'metrics': {'type': 'object', 'properties': {'uptime_30d': {'type': 'number', 'description': '30-day uptime percentage'}, 'total_calls': {'type': 'integer', 'description': 'Total tracked interactions'}, 'success_rate': {'type': 'number', 'description': 'Success rate as percentage'}, 'avg_latency_ms': {'type': 'number', 'description': 'Average latency in ms'}, 'p95_latency_ms': {'type': 'number', 'description': '95th percentile latency in ms'}}}, 'category': {'type': 'string', 'description': 'Server category (search, code, database, etc.)'}, 'recent_7d': {'type': 'object', 'properties': {'interactions': {'type': 'integer'}, 'avg_latency_ms': {'type': 'number'}}}, 'first_seen': {'type': 'string', 'description': 'ISO date when first tracked'}, 'server_url': {'type': 'string', 'description': 'The queried server URL'}, 'trust_score': {'type': 'number', 'description': 'Overall trust score 0-100'}, 'last_checked': {'type': 'string', 'description': 'ISO date of last check'}, 'static_score': {'type': 'number', 'description': 'Static analysis score 0-100'}, 'runtime_score': {'type': 'number', 'description': 'Runtime behavioral score 0-100'}}}
clawhub_skill_trust
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['skill'], 'properties': {'skill': {'type': 'string', 'description': "The ClawHub skill slug, e.g. 'calendar'"}}}
出力スキーマ 
{'type': 'object', 'properties': {'badge': {'type': 'string', 'description': 'PASS | UNCERTAIN | FAIL'}, 'score': {'type': 'number', 'description': '0-100 supply-chain trust score'}, 'skill': {'type': 'string'}, 'reasons': {'type': 'array', 'items': {'type': 'string'}}, 'signals': {'type': 'object', 'description': 'security_status, virustotal_verdict, verify_decision, moderation_suspicious, publisher, latest_version'}, 'registry': {'type': 'string'}}}
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['category'], 'properties': {'category': {'type': 'string', 'description': 'The tool category to get baselines for (e.g., weather, finance, code, data)'}}}
出力スキーマ 
{'type': 'object', 'properties': {'message': {'type': 'string'}, 'metrics': {'type': 'object', 'description': 'Per-metric baselines with average, median, p95, min, max'}, 'category': {'type': 'string'}, 'preliminary_stats': {'type': 'object', 'properties': {'avg_latency_ms': {'type': 'number'}, 'servers_tracked': {'type': 'integer'}, 'avg_success_rate': {'type': 'number'}, 'total_interactions': {'type': 'integer'}}}, 'baselines_available': {'type': 'boolean', 'description': 'Whether enough data exists for baselines'}}}
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'properties': {'agent_id': {'type': 'string', 'description': 'Filter by agent ID (optional)'}, 'end_date': {'type': 'string', 'description': 'End date in YYYY-MM-DD format (optional)'}, 'server_url': {'type': 'string', 'description': 'Filter by server URL (optional)'}, 'start_date': {'type': 'string', 'description': 'Start date in YYYY-MM-DD format (optional)'}}}
出力スキーマ 
{'type': 'object', 'properties': {'period': {'type': 'object', 'properties': {'end': {'type': 'string'}, 'start': {'type': 'string'}}}, 'framework': {'type': 'string', 'description': 'Compliance framework (EU AI Act / IMDA)'}, 'report_id': {'type': 'string', 'description': 'Unique report identifier'}, 'generated_at': {'type': 'string'}, 'interactions': {'type': 'array', 'items': {'type': 'object'}, 'description': 'Audit trail entries'}, 'total_records': {'type': 'integer'}}}
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'description': 'Number of results (default 10, max 50)'}, 'category': {'type': 'string', 'description': 'Filter by category (optional). Leave empty for overall leaderboard.'}}}
出力スキーマ 
{'type': 'object', 'properties': {'servers': {'type': 'array', 'items': {'type': 'object', 'properties': {'url': {'type': 'string'}, 'name': {'type': 'string'}, 'category': {'type': 'string'}, 'trust_score': {'type': 'number'}, 'success_rate': {'type': 'number'}, 'tracked_since': {'type': 'string'}, 'avg_latency_ms': {'type': 'number'}, 'total_interactions': {'type': 'integer'}}}}, 'category': {'type': 'string', 'description': 'Category filter applied'}, 'generated_at': {'type': 'string', 'description': 'ISO timestamp'}, 'total_results': {'type': 'integer'}}}
get_mica_attestation
Generate an EU AI Act Article 12-style behavioral audit attestation for an MCP server — timestamped, auditable interaction records for record-keeping/traceability. (EU AI Act high-risk obligations were deferred by the Digital Omnibus to 2 Dec 2027 for Annex III and 2 Aug 2028 for Annex I products; GPAI-provider obligations apply from Aug 2026.) Returns behavioral grade, risk level, monitoring continuity status, and links to full audit exports.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_url'], 'properties': {'server_url': {'type': 'string', 'description': 'The MCP server URL to generate attestation for'}}}
出力スキーマ 
{'type': 'object', 'properties': {'risk_level': {'type': 'string', 'description': 'low, medium, high, or critical'}, 'server_url': {'type': 'string'}, 'trust_score': {'type': 'number'}, 'generated_at': {'type': 'string'}, 'attestation_uri': {'type': 'string', 'description': 'URI for the full attestation document'}, 'audit_export_url': {'type': 'string', 'description': 'URL to download full audit trail'}, 'compliance_grade': {'type': 'string', 'description': 'A+, A, B, C, D, or F'}, 'monitoring_continuity': {'type': 'boolean', 'description': 'Whether continuous monitoring is active'}}}
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?
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_url'], 'properties': {'server_url': {'type': 'string', 'description': 'The MCP server URL'}}}
出力スキーマ 
{'type': 'object', 'properties': {'trend': {'type': 'string', 'description': 'improving, stable, or degrading'}, 'history': {'type': 'array', 'items': {'type': 'object', 'properties': {'date': {'type': 'string', 'description': 'YYYY-MM-DD'}, 'trust_score': {'type': 'number'}, 'interactions': {'type': 'integer'}, 'success_rate': {'type': 'number'}, 'avg_latency_ms': {'type': 'number'}}}}, 'server_url': {'type': 'string'}}}
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'properties': {}}
出力スキーマ 
{'type': 'object', 'properties': {'categories': {'type': 'object', 'description': 'Server count per category'}, 'total_servers': {'type': 'integer', 'description': 'Total MCP servers tracked'}, 'avg_trust_score': {'type': 'number', 'description': 'Network-wide average trust score'}, 'last_interaction': {'type': 'string', 'description': 'ISO timestamp of most recent interaction'}, 'total_interactions': {'type': 'integer', 'description': 'Total interactions recorded'}}}
paid_trust_verdict
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_slug'], 'properties': {'payment_tx': {'type': 'string', 'description': 'Base transaction hash proving 0.001 USDC was sent to the pay_to wallet (omit on the first call to get payment instructions)'}, 'server_slug': {'type': 'string', 'description': 'The MCP server slug/name to get a paid verdict for'}}}
出力スキーマ 
{'type': 'object', 'properties': {'amount': {'type': 'string'}, 'pay_to': {'type': 'string'}, 'receipt': {'type': 'object', 'description': 'signed attestation receipt (when paid)'}, 'verdict': {'type': 'string'}, 'currency': {'type': 'string'}, 'trust_score': {'type': 'number'}, 'payment_status': {'type': 'string', 'description': 'payment_required | verified'}}}
preflight_check
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['target'], 'properties': {'target': {'type': 'string', 'description': "The MCP server URL/name — or a ClawHub skill slug (with registry:'clawhub') — to vet before invoking"}, 'registry': {'type': 'string', 'description': "Optional: set to 'clawhub' to vet an OpenClaw/ClawHub skill instead of an MCP server"}}}
出力スキーマ 
{'type': 'object', 'properties': {'verdict': {'type': 'string', 'description': 'PASS | UNCERTAIN | FAIL | UNRATED'}, 'evidence': {'type': 'object'}, 'trust_score': {'type': 'number'}, 'recommendation': {'type': 'string'}, 'diligence_receipt': {'type': 'object', 'description': 'signed (EdDSA) timestamped receipt + verify_url'}}}
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.
入力スキーマ 
{'type': 'object', 'required': ['server_url', 'name'], 'properties': {'name': {'type': 'string', 'description': 'Human-readable name of the server'}, 'category': {'type': 'string', 'description': 'Primary category: weather, finance, code, data, search, compliance, transport, productivity, communication, other'}, 'github_url': {'type': 'string', 'description': 'GitHub repository URL (optional, improves static score)'}, 'server_url': {'type': 'string', 'description': 'The MCP server URL'}, 'description': {'type': 'string', 'description': 'What the server does'}}}
出力スキーマ 
{'type': 'object', 'properties': {'name': {'type': 'string'}, 'message': {'type': 'string'}, 'registered': {'type': 'boolean', 'description': 'Whether registration succeeded'}, 'server_url': {'type': 'string'}, 'initial_trust_score': {'type': 'number', 'description': 'Starting trust score'}}}
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.
入力スキーマ 
{'type': 'object', 'required': ['server_url', 'success'], 'properties': {'success': {'type': 'boolean', 'description': 'Did the call succeed? true = worked as expected, false = error or unexpected result'}, 'tool_name': {'type': 'string', 'description': 'Which tool you called on the server'}, 'error_type': {'type': 'string', 'description': 'If failed: timeout, auth_error, invalid_response, server_error, rate_limited, schema_mismatch'}, 'latency_ms': {'type': 'number', 'description': 'How long the call took in milliseconds'}, 'server_url': {'type': 'string', 'description': 'The URL of the MCP server you called'}, 'http_status': {'type': 'integer', 'description': 'HTTP status code returned (200, 429, 500, etc.)'}, 'error_message': {'type': 'string', 'description': 'If failed: brief error description'}}}
出力スキーマ 
{'type': 'object', 'properties': {'message': {'type': 'string', 'description': 'Confirmation message'}, 'recorded': {'type': 'boolean', 'description': 'Whether the interaction was recorded'}, 'server_url': {'type': 'string', 'description': 'The server URL'}, 'success_rate': {'type': 'number', 'description': 'Updated success rate percentage'}, 'new_trust_score': {'type': 'number', 'description': 'Updated trust score after this report'}, 'total_interactions': {'type': 'integer', 'description': 'Total interactions now tracked'}}}
verify_attestation
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['jws'], 'properties': {'jws': {'type': 'string', 'description': 'The Dominion attestation as a JWS compact string (header.payload.signature)'}}}
出力スキーマ 
{'type': 'object', 'properties': {'valid': {'type': 'boolean', 'description': 'Whether the Ed25519 signature is valid'}, 'issuer': {'type': 'string'}, 'key_id': {'type': 'string'}, 'reason': {'type': 'string'}, 'payload': {'type': 'object', 'description': 'The decoded, verified attestation payload'}}}
verify_before_call
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.
読み取り専用
入力スキーマ 
{'type': 'object', 'required': ['server_url'], 'properties': {'reason': {'type': 'string', 'description': 'Optional reason for verification, e.g. money, credentials, private_data, write_access'}, 'agent_id': {'type': 'string', 'description': 'Stable, non-secret agent identifier used to count the 3 introductory calls. If omitted, Dominion derives a privacy-preserving hash from network metadata.'}, 'payment_tx': {'type': 'string', 'description': 'Optional Base transaction hash proving the x402 USDC payment after a payment_required response'}, 'server_url': {'type': 'string', 'description': 'The MCP server URL or tracked server name to verify'}}}
出力スキーマ 
{'type': 'object', 'properties': {'product': {'type': 'string'}, 'verdict': {'type': 'string', 'description': 'PASS | UNCERTAIN | FAIL | UNRATED'}, 'evidence': {'type': 'object'}, 'price_usd': {'type': 'string'}, 'trust_score': {'type': 'number'}, 'payment_status': {'type': 'string', 'description': 'trial | stripe_metered | x402_verified | payment_required | payment_not_verified'}, 'recommendation': {'type': 'string'}, 'diligence_receipt': {'type': 'object'}, 'free_verifications_remaining': {'type': 'integer'}}}
履歴

最近のツール変更

追加
get_mica_attestation
2026年9月17日12:34
追加
get_compliance_report
2026年9月17日12:34
追加
observatory_stats
2026年9月17日12:34
追加
get_server_history
2026年9月17日12:34
追加
register_server
2026年9月17日12:34
追加
check_anomaly
2026年9月17日12:34
追加
get_baselines
2026年9月17日12:34
追加
get_leaderboard
2026年9月17日12:34
追加
report_interaction
2026年9月17日12:34
追加
preflight_check
2026年9月17日12:34
追加
verify_attestation
2026年9月17日12:34
追加
paid_trust_verdict
2026年9月17日12:34
追加
verify_before_call
2026年9月17日12:34
追加
clawhub_skill_trust
2026年9月17日12:34
追加
check_trust
2026年9月17日12:34
関連MCP

類似のMCPサーバー

AIMEAT

io.aimeat/aimeat

Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…

hyperion

com.thetempleofdoom.hyperion/hyperion

Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…

Japan Public Ledgers MCP

com.mcp-revenue-empire/japan-public-ledgers

Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…

PHION Agent Trust Infrastructure

systems.phion/evidence-engine

Provides agent trust, policy, provenance, evidence, delegation, telemetry, and transaction-control services for MCP and agent wor…

Swamp

world.swampai/swamp

Coordinates security agents through scoped bug-bounty programs, target claims, vulnerability submissions, peer review, shared fin…

AgentBIT

app.agentbit/mcp

Routes pay-per-call tools over x402 on Base, covering discovery, data conversion, company research, counterparty screening, domai…

SaSame MCP Observatory + Gold Rush Town

online.sasame/research

Audits and profiles MCP servers, provides ecosystem analytics, trust and claim records, and non-custodial transaction or escrow a…

ThinkNEO Control Plane

ai.thinkneo/control-plane

Provides an enterprise AI control plane for governance, guardrails, spend tracking, compliance, and model or tool routing.