MCPサーバー

Quesen Deterministic Agent Decision Layer

io.github.Shxnque/quesen
AI・エージェント 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

Provides deterministic risk validation and proceed, review, or skip decisions for autonomous-agent actions, with simulation and outcome reporting.

quesen.health
Liveness probe. Returns engine_version and transport.
入力スキーマ
{'type': 'object', 'additionalProperties': False}
quesen.report
Post-decision outcome feedback. Accepts request_id + outcome (RUG/LOSS/OK/WIN/UNKNOWN) plus optional post-trade metadata. Aggregated deterministically for SKIP-rate vs realized-outcome correlation.
入力スキーマ
{'type': 'object', 'required': ['request_id', 'outcome'], 'properties': {'notes': {'type': ['string', 'null'], 'maxLength': 1000, 'description': 'Optional free-text notes about the outcome (post-mortem, context, references). Stored verbatim for audit.'}, 'venue': {'type': ['string', 'null'], 'maxLength': 64, 'description': "Venue or platform where the trade/signal was executed (e.g. 'raydium', 'jupiter', 'uniswap-v3'). Free-form label for downstream grouping."}, 'outcome': {'enum': ['RUG', 'LOSS', 'OK', 'WIN', 'UNKNOWN'], 'type': 'string', 'description': 'Real-world outcome once known. RUG = rug-pull / total loss; LOSS = negative PnL; OK = neutral / no material result; WIN = positive PnL; UNKNOWN = outcome not yet observable.'}, 'request_id': {'type': 'string', 'maxLength': 128, 'minLength': 1, 'description': 'The `request_id` returned by a prior quesen.validate call. Ties the reported outcome back to the exact decision that produced it.'}, 'signal_hash': {'type': ['string', 'null'], 'maxLength': 128, 'description': "Optional hash/fingerprint of the original signal (URL, token address, message id) so outcomes can be joined across systems that don't share Quesen request_ids."}, 'realized_pnl': {'type': ['number', 'null'], 'description': "Realized profit/loss in the caller's chosen unit (e.g. USD, SOL, ETH). Sign convention: positive = profit, negative = loss. Fed into the aggregate `pnl_mean` counter."}, 'elapsed_seconds': {'type': ['integer', 'null'], 'minimum': 0, 'description': 'Seconds elapsed between the original quesen.validate decision and the observation of this outcome. Non-negative.'}, 'client_request_id': {'type': ['string', 'null'], 'maxLength': 128, 'description': 'Optional caller-side trace id. Echoed verbatim in the response for cross-system correlation.'}}, 'additionalProperties': False}
quesen.simulate
Counterfactual scoring. Compare the baseline decision against a simulated decision under caller-supplied weights_override / thresholds_override. Free sales asset — not charged against key.
入力スキーマ
{'type': 'object', 'properties': {'domain_age_days': {'type': ['integer', 'null'], 'minimum': 0, 'description': 'Age of the target domain in days. Same feature as quesen.validate; combined with the (possibly overridden) weights to produce a counterfactual risk score.'}, 'engagement_ratio': {'type': ['number', 'null'], 'maximum': 1.0, 'minimum': 0.0, 'description': 'Engagement ratio in [0, 1]. Same feature as quesen.validate; used with the (possibly overridden) weights during simulation.'}, 'weights_override': {'type': ['object', 'null'], 'properties': {'domain_age': {'type': 'number', 'description': 'Weight applied to the domain_age_days feature during counterfactual scoring.'}, 'engagement': {'type': 'number', 'description': 'Weight applied to the engagement_ratio feature during counterfactual scoring.'}, 'scam_keywords': {'type': 'number', 'description': 'Weight applied to the scam_keyword_count feature during counterfactual scoring.'}}, 'description': 'Optional per-feature weight override used ONLY for this simulation. When null (or omitted) the engine uses its production weights. Does NOT mutate global state.', 'additionalProperties': False}, 'client_request_id': {'type': ['string', 'null'], 'maxLength': 128, 'description': 'Optional caller-side trace id. Echoed verbatim in the response for cross-system correlation.'}, 'scam_keyword_count': {'type': ['integer', 'null'], 'minimum': 0, 'description': 'Count of known scam keywords detected. Same feature as quesen.validate; used with the (possibly overridden) weights.'}, 'thresholds_override': {'type': ['object', 'null'], 'properties': {'skip': {'type': 'number', 'description': 'Risk score at or above which the counterfactual decision becomes SKIP.'}, 'review': {'type': 'number', 'description': 'Risk score at or above which the counterfactual decision becomes REVIEW (below `skip`).'}}, 'description': 'Optional decision-threshold override used ONLY for this simulation. When null the engine uses its production thresholds. Does NOT mutate global state.', 'additionalProperties': False}}, 'additionalProperties': False}
quesen.validate
Deterministic pre-decision risk validation for autonomous agents. Returns PROCEED / REVIEW / SKIP plus risk_score, confidence, and named conflict triggers. Same input -> same output; every response embeds engine_version + weights + thresholds for full replay.
入力スキーマ
{'type': 'object', 'properties': {'domain_age_days': {'type': ['integer', 'null'], 'minimum': 0, 'description': 'Age of the target domain in days.'}, 'engagement_ratio': {'type': ['number', 'null'], 'maximum': 1.0, 'minimum': 0.0, 'description': 'Engagement ratio in [0, 1].'}, 'client_request_id': {'type': ['string', 'null'], 'maxLength': 128, 'description': 'Optional caller-side trace id (echoed in response).'}, 'scam_keyword_count': {'type': ['integer', 'null'], 'minimum': 0, 'description': 'Count of known scam keywords detected.'}}, 'additionalProperties': False}
quesen.version
Full engine configuration — weights, thresholds, versions.
入力スキーマ
{'type': 'object', 'additionalProperties': False}
追加
quesen.version
2026年9月17日12:52
追加
quesen.health
2026年9月17日12:52
追加
quesen.report
2026年9月17日12:52
追加
quesen.simulate
2026年9月17日12:52
追加
quesen.validate
2026年9月17日12:52

GoCreative Agent API

io.github.ColinHughes2121/gocreative-agent-api

Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…

IA-QA — 130+ QA & Dev Tools for AI Agents

io.github.JcJamet/ia-qa-toolbox

Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…

DDG Agent Services

io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp

Acts as a pay-per-call gateway for agent tools including LLM routes, web and market data, Ethereum RPC, security scans, service c…

mainstreet

io.github.philpof102-svg/mainstreet

Provides reputation, trust scoring, validation, consensus, routing, and payment-related tools for on-chain AI agents on Base.

xrpl-referee

io.github.eamwhite1/xrpl-referee

Supports XRPL-based agent hiring, escrow payments, job marketplaces, wallet trust scoring, sanctions and KYC checks, and AI-assis…

InsureLink

io.github.skewing1/insurelink

Manages agent reputation, insurance coverage, SLA agreements, transaction safety checks, attestations, claims, and x402-mediated …

Overwing

ai.overwing/mcp

Evaluates text against configurable safety rules and provides agent policy decisions, approval workflows, compensating actions, a…

Hermes Plant — Agent Commerce Assurance

io.github.JesseGdotIO/hermes-plant

Preflights and attests consequential agent actions, verifies signed evidence, evaluates payments and wallets, and provides determ…