이 MCP로 할 수 있는 일
Compiles natural-language policies into formal SMT guardrails, checks actions and logic, and produces verifiable proofs.
도구
입력 스키마
{'type': 'object', 'required': ['policy_id', 'action', 'api_key'], 'properties': {'action': {'type': 'string', 'description': 'The agent action to verify against the policy (max 2000 chars)'}, 'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID from make_rules'}}}
입력 스키마
{'type': 'object', 'required': ['policy_id', 'action'], 'properties': {'action': {'type': 'string', 'description': 'The agent action to verify against the policy (max 2000 chars)'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID from make_rules'}}}
입력 스키마
{'type': 'object', 'required': ['reasoning'], 'properties': {'show_smt': {'type': 'boolean', 'description': 'Include the generated SMT-LIB2 formula in the response for inspection (default: false)'}, 'reasoning': {'type': 'string', 'description': 'The reasoning, plan, or chain of thought to check. Be specific — include numbers, conditions, and constraints for the best results (max 2000 chars)'}}}
입력 스키마
{'type': 'object', 'required': ['policy_id', 'action', 'api_key'], 'properties': {'action': {'type': 'string', 'description': 'The agent action to screen (max 2000 chars)'}, 'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID from make_rules'}, 'threshold': {'type': 'number', 'description': 'Relevance threshold (0.0 to 1.0). Default 0.0 — any match triggers should_check. Optional.'}}}
입력 스키마
{'type': 'object', 'required': ['username'], 'properties': {'username': {'type': 'string', 'pattern': '^[a-zA-Z0-9_-]{1,32}$', 'description': 'Unique username (1-32 chars, alphanumeric + hyphens/underscores)'}}}
입력 스키마
{'type': 'object', 'required': ['username'], 'properties': {'username': {'type': 'string', 'description': 'Unique username (1-32 chars, alphanumeric + hyphens/underscores)'}}}
입력 스키마
{'type': 'object', 'required': ['policy_id', 'api_key'], 'properties': {'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID from make_rules'}}}
입력 스키마
{'type': 'object', 'required': ['policy', 'api_key'], 'properties': {'policy': {'type': 'string', 'description': "Your policy in plain English, e.g. 'No action may access user data without explicit consent. External API calls require approval above $100.' Up to 50 rules."}, 'api_key': {'type': 'string', 'description': 'Your ICME API key (from create_account or create_account_card)'}}}
입력 스키마
{'type': 'object', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'The session_id returned by create_account_card or top_up_card'}}}
입력 스키마
{'type': 'object', 'required': ['policy_id', 'action', 'api_key'], 'properties': {'action': {'type': 'string', 'description': 'The agent action to check (max 2000 chars)'}, 'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID from make_rules'}}}
입력 스키마
{'type': 'object', 'required': ['policy_id', 'api_key'], 'properties': {'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'policy_id': {'type': 'string', 'format': 'uuid', 'description': 'Policy ID to test'}}}
입력 스키마
{'type': 'object', 'required': ['api_key'], 'properties': {'api_key': {'type': 'string', 'description': 'Your ICME API key'}}}
입력 스키마
{'type': 'object', 'required': ['amount_usd', 'api_key'], 'properties': {'api_key': {'type': 'string', 'description': 'Your ICME API key'}, 'amount_usd': {'type': 'integer', 'description': 'Top-up amount in USD: 5, 10, 25, 50, or 100'}}}
입력 스키마
{'type': 'object', 'required': ['proof_id'], 'properties': {'proof_id': {'type': 'string', 'format': 'uuid', 'description': 'The proof_id returned by a prior check_action or check_action_paid call'}}}
최근 도구 변경
유사한 MCP 서버
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…
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…
validoria-mcp
Runs continuous website, API, and webshop tests covering security, SEO, performance, accessibility, browser journeys, and inciden…
HubVibe: Pay-per-Call Tools for AI Agents: Web Search, Email Verify, KYC, Stocks, Crypto, News, Data
Offers paid utilities for web audits, HTTP fetching and extraction, BigQuery analysis, LLM processing, code execution, blockchain…
developer-tools
Provides general-purpose developer utilities for encoding, hashing, encryption, JSON, HTML, CSS, networking, and related data tra…
Qiniso
Provides deterministic formatting, parsing, holiday and tax lookups, address handling, and checksum or structure validation for i…
ContrastAPI
Provides security research and assessment tools covering CVEs, IOCs, dependencies, secrets, injection risks, HTTP headers, domain…