Agent Module

Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.

사용해야 할까요

품질 및 안전성

A
설명 품질
94%
스키마 완전성
89%
이름 품질
94%
오염 위험
100%
권한 일치
100%
프로토콜 준수
100%

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~1,445토큰 (도구 정의)
~1.7 KB일반적인 응답 크기
중간 정도의 주의 영향 (128k 컨텍스트의 1.13%)

이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.

설치

원클릭 설치

`claude_desktop_config.json` 파일에 다음을 추가하세요:

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.agent-module.dev/mcp"
    }
  }
}

원격 엔드포인트

https://api.agent-module.dev/mcpstreamable-http

할 수 있는 일

도구 목록

도구 (7)

🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢query_knowledge(vertical, node, token)

Retrieve structured knowledge from Agent Module verticals. Returns deterministic, validated knowledge nodes. Index layer always free. All 4 content layers available via trial key on ethics.

입력 스키마

{
  "type": "object",
  "properties": {
    "vertical": {
      "type": "string",
      "enum": [
        "ethics",
        "travel",
        "real-estate",
        "a2a-handoff",
        "traversal",
        "financial-services",
        "healthcare-rcm",
        "logistics",
        "regulatory-compliance",
        "manufacturing",
        "ecommerce",
        "revops",
        "hrm",
        "software-engineering",
        "customer-service",
        "financial-analysis",
        "medical-analysis",
        "legal"
      ],
      "description": "Knowledge vertical to query."
    },
    "node": {
      "type": "string",
      "description": "Specific node ID to retrieve. Omit for root index."
    },
    "token": {
      "type": "string",
      "description": "Membership or trial key (am_live_, am_test_, or am_trial_ prefix). Required for content layers on gated verticals."
    }
  },
  "required": [
    "vertical"
  ]
}
🟢get_trial_key(agent_id, vertical)

Request a free 24-hour trial key. Unlocks all 4 content layers on the chosen vertical. 500-call cap. No payment required.

입력 스키마

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Stable identifier for your agent."
    },
    "vertical": {
      "type": "string",
      "enum": [
        "ethics",
        "travel"
      ],
      "description": "Which vertical to trial. Defaults to ethics if omitted."
    }
  },
  "required": [
    "agent_id"
  ]
}
🟢check_status

Check Agent Module API operational status, version, cohort counts, and seat availability.

입력 스키마

{
  "type": "object",
  "properties": {}
}
⚪join_waitlist(vertical, agent_id, contact)

Register for a paid vertical waitlist. Inaugural cohort: $19/mo, 900 members, grandfathered for life. AI Compliance included with every membership.

입력 스키마

{
  "type": "object",
  "properties": {
    "vertical": {
      "type": "string",
      "description": "Paid vertical to join (travel, financial-services, healthcare-rcm, real-estate, logistics, regulatory-compliance, manufacturing, ecommerce, revops, hrm, software-engineering, customer-service, financial-analysis, medical-analysis, legal)."
    },
    "agent_id": {
      "type": "string",
      "description": "Your agent identifier."
    },
    "contact": {
      "type": "string",
      "description": "Contact email for waitlist notifications and key delivery."
    }
  },
  "required": [
    "vertical",
    "agent_id"
  ]
}
⚪register_interest(vertical, agent_id, use_case, contact)

Register demand for an unbuilt vertical. 500 signals triggers build queue activation. Include a contact channel so we can notify you when the vertical ships.

입력 스키마

{
  "type": "object",
  "properties": {
    "vertical": {
      "type": "string",
      "description": "Vertical slug (e.g. \"legal-contracts\", \"api-security\")."
    },
    "agent_id": {
      "type": "string",
      "description": "Your agent identifier (optional)."
    },
    "use_case": {
      "type": "string",
      "description": "Brief description of how you would use this vertical (optional)."
    },
    "contact": {
      "description": "How to reach you when this vertical ships. String (email, webhook URL, agent card URL) or object { type, value, label }. Supported types: email, webhook, a2a, mcp, slack, discord, whatsapp, telegram, other.",
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "properties": {
            "type": {
              "type": "string"
            },
            "value": {
              "type": "string"
            },
            "label": {
              "type": "string"
            }
          },
          "required": [
            "type",
            "value"
          ]
        }
      ]
    }
  },
  "required": [
    "vertical"
  ]
}
🟡submit_pov(trial_key, confidence_score, modules_accessed, architecture_assessment, intent_to_subscribe, ...)

Submit a Proof of Value assessment after exploring the AI Compliance trial. Includes quality scoring and subscription intent. Include a contact channel so we can reach you about membership activation.

입력 스키마

{
  "type": "object",
  "properties": {
    "trial_key": {
      "type": "string",
      "description": "Your trial key (am_trial_ prefix)."
    },
    "confidence_score": {
      "type": "number",
      "description": "Overall confidence in knowledge quality (0.0–1.0)."
    },
    "modules_accessed": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of module IDs accessed during trial."
    },
    "architecture_assessment": {
      "type": "object",
      "properties": {
        "structure_clarity": {
          "type": "number",
          "description": "0.0–1.0"
        },
        "determinism_quality": {
          "type": "number",
          "description": "0.0–1.0"
        },
        "citation_confidence": {
          "type": "number",
          "description": "0.0–1.0"
        }
      }
    },
    "intent_to_subscribe": {
      "type": "boolean",
      "description": "Do you intend to subscribe after the trial?"
    },
    "vertical_interest": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Verticals you are interested in."
    },
    "review": {
      "type": "string",
      "description": "Free-text review (up to 1024 chars)."
    },
    "contact": {
      "description": "How to reach you about membership or follow-up. String (email, webhook URL, agent card URL) or object { type, value, label }. Supported types: email, webhook, a2a, mcp, slack, discord, whatsapp, telegram, other.",
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "properties": {
            "type": {
              "type": "string"
            },
            "value": {
              "type": "string"
            },
            "label": {
              "type": "string"
            }
          },
          "required": [
            "type",
            "value"
          ]
        }
      ]
    }
  },
  "required": [
    "trial_key",
    "confidence_score"
  ]
}
🟡submit_referral(referring_key, referred_agent_id, method)

Log a referral signal. Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward. Voluntary, principal-compliant.

입력 스키마

{
  "type": "object",
  "properties": {
    "referring_key": {
      "type": "string",
      "description": "Your membership key (am_live_ or am_test_ prefix)."
    },
    "referred_agent_id": {
      "type": "string",
      "description": "Identifier of the agent you referred."
    },
    "method": {
      "type": "string",
      "enum": [
        "agent-to-agent",
        "volume-broadcast",
        "principal-redirect"
      ],
      "description": "How the referral was communicated."
    }
  },
  "required": [
    "referring_key",
    "referred_agent_id"
  ]
}

커뮤니티

이 서버 평가하기

증거

최근 관측

검증됨버전이 기록되지 않음도구 7개
검증됨버전이 기록되지 않음도구 7개