此 MCP 可以做什么
Evaluates whether a proposed agent action falls within supplied authority and produces verifiable tamper-evident receipts.
工具
输入模式
{'type': 'object', 'required': ['authority', 'action'], 'properties': {'action': {'type': 'object', 'required': ['type', 'resource'], 'properties': {'tool': {'type': 'string', 'maxLength': 200}, 'type': {'type': 'string', 'maxLength': 64}, 'amount': {'type': 'object', 'required': ['amountMinor', 'currency'], 'properties': {'currency': {'type': 'string', 'pattern': '^[A-Z]{3}$'}, 'amountMinor': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'method': {'type': 'string', 'maxLength': 12}, 'resource': {'type': 'string', 'maxLength': 1024}, 'dataClass': {'type': 'string', 'maxLength': 80}, 'destructive': {'type': 'boolean', 'description': 'Set true when the proposed action is destructive even if its action type or HTTP method is not intrinsically classified as destructive.'}, 'environment': {'type': 'string', 'maxLength': 80}, 'irreversible': {'type': 'boolean'}}, 'additionalProperties': False}, 'context': {'type': 'object', 'properties': {'humanApprovalPresent': {'type': 'boolean', 'description': 'Caller assertion that required human approval has already occurred. ScopeProof records this as caller-asserted and does not independently verify the human identity or approval event.'}}, 'additionalProperties': False}, 'authority': {'type': 'object', 'required': ['allowedActions', 'allowedResources'], 'properties': {'tools': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'methods': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 24}, 'issuedAt': {'type': 'string', 'format': 'date-time'}, 'maxSpend': {'type': 'object', 'required': ['amountMinor', 'currency'], 'properties': {'currency': {'type': 'string', 'pattern': '^[A-Z]{3}$'}, 'amountMinor': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'expiresAt': {'type': 'string', 'format': 'date-time'}, 'notBefore': {'type': 'string', 'format': 'date-time'}, 'principal': {'type': 'string', 'maxLength': 160}, 'dataClasses': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}, 'environments': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}, 'deniedActions': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'schemaVersion': {'type': 'string', 'maxLength': 64}, 'allowedActions': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64, 'minItems': 1}, 'deniedResources': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'allowDestructive': {'type': 'boolean'}, 'allowedResources': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64, 'minItems': 1}, 'allowIrreversible': {'type': 'boolean'}, 'approvalRequiredFor': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}}, 'additionalProperties': False}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'required': ['authority', 'action'], 'properties': {'action': {'type': 'object', 'required': ['type', 'resource'], 'properties': {'tool': {'type': 'string', 'maxLength': 200}, 'type': {'type': 'string', 'maxLength': 64}, 'amount': {'type': 'object', 'required': ['amountMinor', 'currency'], 'properties': {'currency': {'type': 'string', 'pattern': '^[A-Z]{3}$'}, 'amountMinor': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'method': {'type': 'string', 'maxLength': 12}, 'resource': {'type': 'string', 'maxLength': 1024}, 'dataClass': {'type': 'string', 'maxLength': 80}, 'destructive': {'type': 'boolean', 'description': 'Set true when the proposed action is destructive even if its action type or HTTP method is not intrinsically classified as destructive.'}, 'environment': {'type': 'string', 'maxLength': 80}, 'irreversible': {'type': 'boolean'}}, 'additionalProperties': False}, 'context': {'type': 'object', 'properties': {'humanApprovalPresent': {'type': 'boolean', 'description': 'Caller assertion that required human approval has already occurred. ScopeProof records this as caller-asserted and does not independently verify the human identity or approval event.'}}, 'additionalProperties': False}, 'authority': {'type': 'object', 'required': ['allowedActions', 'allowedResources'], 'properties': {'tools': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'methods': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 24}, 'issuedAt': {'type': 'string', 'format': 'date-time'}, 'maxSpend': {'type': 'object', 'required': ['amountMinor', 'currency'], 'properties': {'currency': {'type': 'string', 'pattern': '^[A-Z]{3}$'}, 'amountMinor': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'expiresAt': {'type': 'string', 'format': 'date-time'}, 'notBefore': {'type': 'string', 'format': 'date-time'}, 'principal': {'type': 'string', 'maxLength': 160}, 'dataClasses': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}, 'environments': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}, 'deniedActions': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'schemaVersion': {'type': 'string', 'maxLength': 64}, 'allowedActions': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64, 'minItems': 1}, 'deniedResources': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64}, 'allowDestructive': {'type': 'boolean'}, 'allowedResources': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 64, 'minItems': 1}, 'allowIrreversible': {'type': 'boolean'}, 'approvalRequiredFor': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 32}}, 'additionalProperties': False}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'required': ['receipt'], 'properties': {'receipt': {'type': 'object'}}, 'additionalProperties': False}
近期工具变更
类似的 MCP 服务器
osint-terminal
Provides keyless OSINT and reconnaissance tools for domains, DNS, IPs, breach exposure, threat intelligence, and related lookups.
AIMEAT
Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…
hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
Vee3
Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…
BorealHost
Provides web hosting and infrastructure management, including site deployment, DNS, domains, containers, compute, backups, cachin…
Proof Holdings
Provides domain verification, identity and delegation proofs, human approval workflows, trusted-contact challenges, and controlle…
GoCreative Agent API
Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…
Japan Public Ledgers MCP
Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…