このMCPでできること
Verifies agent actions against policies and creates cryptographic attestations, provenance chains, intent bindings, release tokens, and compliance evidence.
機能
ツール
9
ツール
attest
Attest Action
Create a hash-chained provenance record for an action you've taken. Each attestation extends the append-only evidence chain. The hash can be independently verified by any third party. Cost: $0.02 per call.
入力スキーマ
{'type': 'object', 'required': ['agent_id', 'action_description', 'action_payload'], 'properties': {'context': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': 'Optional metadata such as environment, trigger, or session info'}, 'agent_id': {'type': 'string', 'description': 'Unique identifier of the attesting agent'}, 'action_payload': {'type': 'object', 'description': 'Structured data describing the action (hashed into provenance)', 'additionalProperties': True}, 'action_description': {'type': 'string', 'description': 'Human-readable description of the action taken'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
bind
Bind Intent to Command
Declare an intent and cryptographically bind it to a command. Proves that the command was issued in service of the declared intent. Use verify-outcome after execution to close the loop. Cost: $0.02 per call.
入力スキーマ
{'type': 'object', 'required': ['agent_id', 'intent_type', 'intent_description', 'command_payload'], 'properties': {'agent_id': {'type': 'string', 'description': 'Unique identifier of the agent declaring intent'}, 'goal_state': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': 'Expected end state for outcome verification'}, 'intent_type': {'type': 'string', 'description': "Category of intent (e.g. 'navigation', 'transaction', 'deployment')"}, 'intent_source': {'type': 'string', 'default': 'AI_PLANNER', 'description': 'Origin of intent: AI_PLANNER, HUMAN_OPERATOR, or SYSTEM'}, 'command_payload': {'type': 'object', 'description': 'The command that will be executed to fulfill this intent', 'additionalProperties': True}, 'parent_intent_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ID of parent intent for hierarchical intent chains'}, 'intent_description': {'type': 'string', 'description': 'Human-readable description of what the agent intends to do'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
bundle
Generate Compliance Bundle
Generate a certifier-grade compliance evidence bundle. Contains hash-chained provenance, intent bindings, PQC attestations, and verification instructions. Independently verifiable without Kevros access. Cost: $0.05 per call.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent whose provenance records to include in the bundle'}, 'max_records': {'type': 'integer', 'default': 10000, 'description': 'Maximum number of provenance records to include'}, 'time_range_end': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO 8601 end time filter (inclusive)'}, 'time_range_start': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO 8601 start time filter (inclusive)'}, 'include_intent_chains': {'type': 'boolean', 'default': True, 'description': 'Include intent-command binding chains in the bundle'}, 'include_pqc_signatures': {'type': 'boolean', 'default': True, 'description': 'Include post-quantum ML-DSA-87 block signatures'}, 'include_verification_instructions': {'type': 'boolean', 'default': True, 'description': 'Include step-by-step verification procedure for auditors'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
check-peer
Check Peer Trust
Check another agent's trust score and governance history. Returns trust score (0-100), chain length, attestation count, and tier. Free, no API key needed.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'ID of the peer agent to look up'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
health
Health Check
Check the governance gateway health status. Free.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'properties': {'verbose': {'type': 'boolean', 'default': False, 'description': 'Return additional details such as chain length and PQC signing status'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
status
Trust Status
Check your current usage and quota: calls used, calls remaining, tier, rate limits, and billing status. Free.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'properties': {'include_chain_details': {'type': 'boolean', 'default': False, 'description': 'Include hash-chain integrity check and latest provenance epoch'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
verify
Verify Action
Verify an action against policy bounds before executing it. Returns ALLOW (proceed), CONSTRAIN (proceed with modified values; emitted on the wire as the legacy value CLAMP - both refer to the same verdict, CONSTRAIN is the public name), or DENY (stop). Every verification is recorded in a hash-chained provenance ledger. Cost: $0.01 per call.
冪等
入力スキーマ
{'type': 'object', 'required': ['action_type', 'action_payload', 'agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Unique identifier of the agent requesting verification'}, 'action_type': {'type': 'string', 'description': "Category of action to verify (e.g. 'deploy', 'trade', 'send_email')"}, 'template_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Named policy template (e.g. 'robotics-arm', 'financial-transaction'). Merged with policy_context."}, 'action_payload': {'type': 'object', 'description': 'Action parameters to verify against policy bounds', 'additionalProperties': True}, 'policy_context': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': 'Optional policy overrides such as max_values or forbidden_keys'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional key for idempotent retries - same key returns cached result'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
verify-outcome
Verify Outcome
Verify that an executed action achieved its declared intent. Closes the loop: intent -> command -> action -> outcome -> verification. Free (included with bind).
冪等
入力スキーマ
{'type': 'object', 'required': ['agent_id', 'intent_id', 'binding_id', 'actual_state'], 'properties': {'agent_id': {'type': 'string', 'description': 'Unique identifier of the agent whose outcome is being verified'}, 'intent_id': {'type': 'string', 'description': 'ID of the original intent from governance_bind'}, 'tolerance': {'type': 'number', 'default': 0.1, 'description': 'Numeric tolerance for goal matching (0.1 = 10% deviation allowed)'}, 'binding_id': {'type': 'string', 'description': 'ID of the intent-command binding from governance_bind'}, 'actual_state': {'type': 'object', 'description': 'Observed end state after action execution, compared against goal_state', 'additionalProperties': True}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
verify-token
Verify Release Token
Verify a release token from another agent. Confirms the token is authentic, was issued by the Kevros gateway, and remains currently authorized after any halt or mode transition. Free, no API key needed.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['release_token'], 'properties': {'release_token': {'type': 'string', 'description': 'Release token string received from governance_verify'}, 'token_preimage': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Deprecated. The gateway now performs verification entirely server-side using the release_token alone; any value supplied here is ignored. Field retained for backward compatibility with v1 SDK callers and will be removed in a future release.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
履歴
最近のツール変更
追加
verify-token
2026年9月19日2:44
追加
check-peer
2026年9月19日2:44
追加
status
2026年9月19日2:44
追加
health
2026年9月19日2:44
追加
bundle
2026年9月19日2:44
追加
verify-outcome
2026年9月19日2:44
追加
bind
2026年9月19日2:44
追加
attest
2026年9月19日2:44
追加
verify
2026年9月19日2:44
関連MCP
類似のMCPサーバー
osint-terminal
com.thetempleofdoom.osint-mcp/osint-terminal
Provides keyless OSINT and reconnaissance tools for domains, DNS, IPs, breach exposure, threat intelligence, and related lookups.
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…
Vee3
io.github.Vee3io/vee3
Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…
BorealHost
ai.borealhost/mcp
Provides web hosting and infrastructure management, including site deployment, DNS, domains, containers, compute, backups, cachin…
Proof Holdings
holdings.proof/mcp-server
Provides domain verification, identity and delegation proofs, human approval workflows, trusted-contact challenges, and controlle…
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…
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…