このMCPでできること
Searches, scores, compares, routes, and governs MCP servers and agents, including tool-call authorization, mandates, risk reports, policy export, audit evidence, and drift monitoring.
機能
ツール
22
ツール
compare_servers
Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['identifiers'], 'properties': {'identifiers': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 4, 'minItems': 2, 'description': 'Canonical server identifiers in namespace/name format.'}}}
compile_docs
Generate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page.
入力スキーマ
{'type': 'object', 'required': ['title'], 'properties': {'title': {'type': 'string'}, 'metadata': {'type': 'object'}, 'source_url': {'type': 'string'}, 'source_type': {'enum': ['openapi', 'github_repo', 'markdown', 'postman', 'website', 'pdf', 'help_center', 'mixed'], 'type': 'string'}, 'openapi_spec': {'type': 'object'}, 'website_docs': {'type': 'string'}, 'markdown_docs': {'type': 'string'}, 'policy_metadata': {'type': 'object'}, 'server_identifier': {'type': 'string'}, 'postman_collection': {'type': 'object'}}}
create_mandate
Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints.
入力スキーマ
{'type': 'object', 'required': ['user_id', 'agent_id', 'scope'], 'properties': {'scope': {'type': 'string'}, 'user_id': {'type': 'string'}, 'agent_id': {'type': 'string'}, 'metadata': {'type': 'object'}, 'server_id': {'type': 'string'}, 'signature': {'type': 'string'}, 'constraints': {'type': 'object'}, 'valid_until': {'type': 'string', 'format': 'date-time'}, 'budget_limit': {'type': 'number'}, 'requires_human_approval': {'type': 'boolean'}}}
decide_agent_call
Verify Gateway decision point. Decide whether this agent may call this tool, with this payload, for this user, right now. Writes an audit-ledger decision event.
入力スキーマ
{'type': 'object', 'required': ['agent_id', 'user_id', 'server_id', 'tool'], 'properties': {'tool': {'type': 'string'}, 'action': {'enum': ['invoke', 'read', 'write', 'preview', 'list', 'connect'], 'type': 'string'}, 'client': {'type': 'string'}, 'user_id': {'type': 'string'}, 'agent_id': {'type': 'string'}, 'max_cost': {'type': 'number'}, 'max_risk': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string'}, 'server_id': {'type': 'string', 'description': 'Server identifier in namespace/name format.'}, 'mandate_id': {'type': 'string', 'description': 'Optional Verify Mandate key or id.'}, 'audit_context': {'type': 'object'}, 'requested_cost': {'type': 'number'}, 'requires_oauth': {'type': 'boolean'}, 'max_freshness_hours': {'type': 'number'}, 'max_runtime_seconds': {'type': 'integer'}, 'approval_token_present': {'type': 'boolean'}, 'payload_classification': {'type': 'array', 'items': {'type': 'string'}}, 'no_write_without_approval': {'type': 'boolean'}}}
explain_agent_risk
Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string'}}}
export_policy
Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['identifier'], 'properties': {'client': {'type': 'string'}, 'max_risk': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string'}, 'identifier': {'type': 'string', 'description': 'Canonical server identifier in namespace/name format.'}, 'requires_oauth': {'type': 'boolean'}, 'max_freshness_hours': {'type': 'number'}, 'no_write_without_approval': {'type': 'boolean'}}}
fetch
ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Canonical MCP server identifier in namespace/name format.'}}}
generate_remediation_plan
Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string'}}}
get_agent
Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string'}}}
get_drift_report
Agent Sprawl Radar: return agent drift events across latest snapshots.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'agent_id': {'type': 'string'}}}
get_evidence_pack
Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 1000, 'minimum': 1}, 'user_id': {'type': 'string'}, 'agent_id': {'type': 'string'}, 'server_id': {'type': 'string'}}}
get_gateway_options
Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {}}
get_hosting_options
Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {}}
get_server_report
Return the full machine-readable verify report for a specific MCP server identifier.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['identifier'], 'properties': {'identifier': {'type': 'string', 'description': 'Canonical server identifier in namespace/name format.'}}}
get_subscription_options
Return alert types, subscription channels, watch scopes, and existing subscription endpoints.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {}}
list_agents
Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'risk_level': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string'}}}
list_high_risk_agents
Agent Sprawl Radar: list high and critical risk agents for review.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}}}
recommend_servers
Recommend MCP servers for a plain-language task and return ranked matches with install config.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['task'], 'properties': {'task': {'type': 'string', 'description': "Plain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'."}, 'limit': {'type': 'integer', 'maximum': 20, 'minimum': 1, 'description': 'Maximum number of recommendations to return.'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Optional explicit capability constraints that override or extend the inferred task capabilities.'}, 'client_target': {'enum': ['openai_connectors', 'claude_desktop', 'smithery', 'generic_http', 'healthcare'], 'type': 'string', 'description': 'Optional target client or integration surface.'}, 'risk_tolerance': {'enum': ['any', 'low', 'medium', 'high'], 'type': 'string', 'description': 'How much tool-surface risk is acceptable.'}, 'auth_preference': {'enum': ['any', 'oauth', 'unauthenticated'], 'type': 'string', 'description': 'Preferred auth mode.'}}}
route_task
Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['task'], 'properties': {'task': {'type': 'string', 'description': 'Task the agent wants to perform.'}, 'max_risk': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string', 'description': 'Maximum allowed tool risk.'}, 'candidate': {'type': 'string', 'description': 'Optional namespace/name server identifier to evaluate directly.'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Optional capability constraints such as healthcare, search, database, read, or write.'}, 'client_target': {'enum': ['openai_connectors', 'claude_desktop', 'smithery', 'generic_http', 'healthcare'], 'type': 'string'}, 'requires_oauth': {'type': 'boolean'}, 'max_freshness_hours': {'type': 'number'}, 'no_write_without_approval': {'type': 'boolean'}}}
score_agent
Agent Sprawl Radar: score a normalized agent payload or an existing registry agent.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'agent': {'type': 'object'}, 'agent_id': {'type': 'string'}}}
search
ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'maximum': 20, 'minimum': 1, 'description': 'Maximum number of search results to return.'}, 'query': {'type': 'string', 'description': 'Search query such as healthcare MCP, web search MCP, ChatGPT-compatible MCPs, or OAuth MCP servers.'}}}
search_servers
Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 20, 'minimum': 1, 'description': 'Maximum number of ranked candidates to return.'}, 'query': {'type': 'string', 'description': 'Optional free-text query to bias ranking toward a specific use case or domain.'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Normalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts.'}, 'client_target': {'enum': ['openai_connectors', 'claude_desktop', 'smithery', 'generic_http', 'healthcare'], 'type': 'string', 'description': 'Optional target client or integration surface.'}, 'risk_tolerance': {'enum': ['any', 'low', 'medium', 'high'], 'type': 'string', 'description': 'How much tool-surface risk is acceptable.'}, 'auth_preference': {'enum': ['any', 'oauth', 'unauthenticated'], 'type': 'string', 'description': 'Preferred auth mode. Use unauthenticated when the agent must avoid login flows.'}}}
履歴
最近のツール変更
追加
generate_remediation_plan
2026年9月17日12:53
追加
get_drift_report
2026年9月17日12:53
追加
list_high_risk_agents
2026年9月17日12:53
追加
explain_agent_risk
2026年9月17日12:53
追加
score_agent
2026年9月17日12:53
追加
get_agent
2026年9月17日12:53
追加
list_agents
2026年9月17日12:53
追加
get_hosting_options
2026年9月17日12:53
追加
get_gateway_options
2026年9月17日12:53
追加
get_subscription_options
2026年9月17日12:53
追加
export_policy
2026年9月17日12:53
追加
compile_docs
2026年9月17日12:53
追加
get_evidence_pack
2026年9月17日12:53
追加
create_mandate
2026年9月17日12:53
追加
decide_agent_call
2026年9月17日12:53
追加
route_task
2026年9月17日12:53
追加
compare_servers
2026年9月17日12:53
追加
get_server_report
2026年9月17日12:53
追加
recommend_servers
2026年9月17日12:53
追加
search_servers
2026年9月17日12:53
追加
fetch
2026年9月17日12:53
追加
search
2026年9月17日12:53
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.