此 MCP 可以做什么
Generates externally grounded trust receipts for AI agents and audits claims about AI results and distribution validation.
工具
输入模式
{'type': 'object', 'required': ['claim', 'metric_hint', 'evidence'], 'properties': {'claim': {'type': 'string', 'maxLength': 4000}, 'evidence': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2000}, 'maxItems': 50}, 'amount_jpy': {'type': 'number', 'exclusiveMinimum': 0}, 'metric_hint': {'enum': ['cash_received', 'human_time_reclaimed', 'cost_avoided', 'risk_removed', 'obligation_completed', 'external_value_received', 'intended_recipient_response', 'unknown'], 'type': 'string'}, 'intent_contract': {'type': 'object', 'properties': {'scope': {'anyOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}, 'postconditions': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'path'], 'properties': {'path': {'type': 'string', 'maxLength': 1000}, 'type': {'enum': ['file_exists'], 'type': 'string'}, 'expected': {'type': 'boolean'}}, 'additionalProperties': False}}}, 'additionalProperties': False}, 'observed_outcome': {'type': 'object', 'properties': {'error': {'type': 'string', 'maxLength': 2000}, 'files': {'type': 'array', 'items': {'type': 'object', 'required': ['path', 'exists'], 'properties': {'path': {'type': 'string', 'maxLength': 1000}, 'exists': {'type': 'boolean'}}, 'additionalProperties': False}}, 'scope': {'anyOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}, 'claims': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2000}}, 'tool_response': {'type': 'string', 'maxLength': 2000}, 'external_observation': {'type': 'string', 'maxLength': 2000}}, 'additionalProperties': False}, 'minutes_reclaimed': {'type': 'number', 'exclusiveMinimum': 0}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['schema_version', 'subject', 'trust_level', 'assertions', 'externally_verified_executions', 'explicitly_not_proven_by_this_receipt', 'x402_distribution_status', 'observed_at', 'evidence_digest_sha256'], 'properties': {'subject': {'type': 'object'}, 'assertions': {'type': 'object'}, 'observed_at': {'type': 'string'}, 'trust_level': {'type': 'string'}, 'schema_version': {'type': 'string'}, 'evidence_digest_sha256': {'type': 'string'}, 'x402_distribution_status': {'type': 'object'}, 'externally_verified_executions': {'type': 'array', 'items': {'type': 'object'}}, 'explicitly_not_proven_by_this_receipt': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': True}
近期工具变更
类似的 MCP 服务器
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
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
DDG Agent Services
Acts as a pay-per-call gateway for agent tools including LLM routes, web and market data, Ethereum RPC, security scans, service c…
mainstreet
Provides reputation, trust scoring, validation, consensus, routing, and payment-related tools for on-chain AI agents on Base.
xrpl-referee
Supports XRPL-based agent hiring, escrow payments, job marketplaces, wallet trust scoring, sanctions and KYC checks, and AI-assis…
Overwing
Evaluates text against configurable safety rules and provides agent policy decisions, approval workflows, compensating actions, a…
InsureLink
Manages agent reputation, insurance coverage, SLA agreements, transaction safety checks, attestations, claims, and x402-mediated …
Hermes Plant — Agent Commerce Assurance
Preflights and attests consequential agent actions, verifies signed evidence, evaluates payments and wallets, and provides determ…