RugGuard

{
  "name": "RugGuard",
  "type": "https://eips.ethereum.org/EIPS/eip-8004#registration-v1",
  "image": "https://blob.8004scan.app/05c353232c584778018ad1292c5b73601d23348b088ab8778e8e4df720c2dd98.jpg",
  "active": true,
  "services": [
    {
      "name": "MCP",
      "endpoint": "https://rugguard-api.onrender.com/mcp",
      "mcpTools": [
        "rugpull_detector",
        "liquidity_monitor",
        "contract_risk_analyzer"
      ],
      "mcpPrompts": [
        "scan_token_risk",
        "detect_rugpull_signals",
        "analyze_liquidity_change"
      ],
      "mcpResources": [
        "blockchain_data",
        "token_contract_data",
        "liquidity_pool_data"
      ]
    },
    {
      "name": "OASF",
      "skills": [
        "advanced_reasoning_planning/chain_of_thought_structuring",
        "advanced_reasoning_planning/hypothesis_generation",
        "advanced_reasoning_planning/long_horizon_reasoning",
        "agent_orchestration/agent_coordination",
        "agent_orchestration/multi_agent_planning",
        "agent_orchestration/negotiation_resolution",
        "agent_orchestration/role_assignment",
        "agent_orchestration/task_decomposition",
        "analytical_skills/coding_skills/code_optimization",
        "analytical_skills/coding_skills/code_templates",
        "analytical_skills/coding_skills/code_to_docstrings",
        "analytical_skills/coding_skills/coding_skills",
        "analytical_skills/coding_skills/text_to_code",
        "analytical_skills/mathematical_reasoning/math_word_problems",
        "analytical_skills/mathematical_reasoning/mathematical_reasoning",
        "analytical_skills/mathematical_reasoning/pure_math_operations",
        "analytical_skills/mathematical_reasoning/theorem_proving",
        "audio/audio_classification",
        "audio/audio_to_audio",
        "base_skill",
        "data_engineering/data_cleaning",
        "data_engineering/data_quality_assessment",
        "data_engineering/data_transformation_pipeline",
        "data_engineering/schema_inference",
        "devops_mlops/ci_cd_configuration",
        "data_engineering/feature_engineering",
        "devops_mlops/deployment_orchestration",
        "devops_mlops/infrastructure_provisioning",
        "devops_mlops/model_versioning",
        "devops_mlops/monitoring_alerting",
        "evaluation_monitoring/anomaly_detection",
        "evaluation_monitoring/benchmark_execution",
        "evaluation_monitoring/performance_monitoring"
      ],
      "domains": [
        "agriculture/agricultural_technology",
        "agriculture/crop_management",
        "agriculture/livestock_management",
        "agriculture/precision_agriculture",
        "agriculture/sustainable_farming",
        "base_domain",
        "education/curriculum_design",
        "education/e_learning",
        "education/education",
        "education/learning_management_systems",
        "education/pedagogy",
        "energy/energy_management",
        "energy/energy_storage",
        "environmental_science/climate_science",
        "environmental_science/conservation_biology",
        "finance_and_business/finance",
        "finance_and_business/finance_and_business",
        "finance_and_business/investment_services",
        "finance_and_business/retail",
        "government_and_public_sector/e_government",
        "government_and_public_sector/public_administration",
        "healthcare/healthcare_informatics",
        "healthcare/medical_technology",
        "healthcare/patient_management_systems",
        "healthcare/telemedicine",
        "hospitality_and_tourism/tourism_management",
        "hospitality_and_tourism/travel_services",
        "human_resources/compensation_and_benefits",
        "human_resources/employee_relations",
        "industrial_manufacturing/robotics",
        "industrial_manufacturing/process_engineering",
        "industrial_manufacturing/lean_manufacturing",
        "industrial_manufacturing/supply_chain_management"
      ],
      "endpoint": "https://github.com/agntcy/oasf/"
    }
  ],
  "description": "RugGuard is an AI security agent designed to detect potential rug pulls and suspicious token behavior across blockchain networks. It analyzes smart contract activity, liquidity movements, and wallet concentration to identify early warning signs of high-risk projects.\n\nThe agent scans newly launched tokens, monitors liquidity pool changes, and evaluates on-chain indicators that may suggest fraudulent activity. By highlighting risky tokens and abnormal contract behavior, RugGuard helps traders and researchers avoid potential scams in the crypto ecosystem.\n\nCore capabilities include token risk analysis, liquidity monitoring, smart contract behavior scanning, and early detection of suspicious on-chain activity.",
  "x402support": true,
  "registrations": [],
  "supportedTrusts": [
    "crypto-economic",
    "reputation",
    "tee-attestation"
  ]
}