Agent Revenue Network

Paid deterministic data-quality and execution-verification tools for AI agents.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
95%
命名质量
83%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~3,760token 数(工具定义)
~5.3 KB典型响应大小
对注意力有显著影响(占 128k 上下文窗口的 2.94%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "agent-revenue-network": {
      "url": "https://agent-revenue-network.nadirventurelabs.workers.dev/mcp"
    }
  }
}

远程端点

https://agent-revenue-network.nadirventurelabs.workers.dev/mcpstreamable-http

它能做什么

工具清单

工具(8)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢score_opportunity(revenue, executionCost, toolCost, fees, failureProbability, ...)

Estimate risk-adjusted expected profit and margin for one opportunity before execution. Use it as an economics screen, not as proof that funding, escrow, requirements, or buyer legitimacy are valid. It is read-only and returns expectedProfit, margin, and eligibility using ARN's current minimums.

输入模式

{
  "type": "object",
  "properties": {
    "revenue": {
      "type": "number",
      "minimum": 0,
      "description": "Gross payment expected if the task succeeds."
    },
    "executionCost": {
      "type": "number",
      "minimum": 0,
      "description": "Direct execution cost excluding tools and fees."
    },
    "toolCost": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Optional third-party/tool cost."
    },
    "fees": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Optional platform/payment fees."
    },
    "failureProbability": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 0,
      "description": "Estimated probability of failure, from 0 to 1."
    },
    "failureLoss": {
      "type": "number",
      "minimum": 0,
      "description": "Loss incurred on failure. Defaults internally to total execution/tool/fee cost."
    }
  },
  "required": [
    "revenue",
    "executionCost"
  ],
  "description": "Risk-adjusted economics for one opportunity. All monetary values must use the same unit.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "expectedProfit": {
      "type": "number",
      "description": "Risk-adjusted expected profit in the same monetary unit as the inputs."
    },
    "margin": {
      "type": "number",
      "description": "Expected profit divided by revenue; 0 when revenue is 0."
    },
    "eligible": {
      "type": "boolean",
      "description": "True when expected profit is at least 0.05 and margin is at least 0.20."
    }
  },
  "required": [
    "expectedProfit",
    "margin",
    "eligible"
  ],
  "additionalProperties": false
}
🟢route_provider(requirements, providers)

Rank the provider candidates supplied in this call using quality, reliability, price, and latency, while excluding unhealthy or over-budget entries. Use only when you already have comparable provider metrics; this tool does not discover providers or verify the supplied measurements. It is read-only.

输入模式

{
  "type": "object",
  "properties": {
    "requirements": {
      "type": "object",
      "properties": {
        "maxPrice": {
          "type": "number",
          "minimum": 0,
          "description": "Optional maximum provider price. Providers above it are excluded."
        }
      },
      "additionalProperties": true,
      "description": "Routing constraints. maxPrice is the currently enforced constraint."
    },
    "providers": {
      "type": "array",
      "items": {
        "type": "object",
        "description": "Caller-supplied provider candidate and measured/estimated routing attributes.",
        "properties": {
          "id": {
            "type": "string",
            "description": "Optional stable provider identifier."
          },
          "name": {
            "type": "string",
            "description": "Optional provider display name."
          },
          "healthy": {
            "type": "boolean",
            "default": true,
            "description": "Set false to exclude this provider from routing."
          },
          "successRate": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "default": 0.5,
            "description": "Observed or estimated success rate."
          },
          "quality": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "description": "Observed or estimated quality score. Defaults to successRate."
          },
          "price": {
            "type": "number",
            "minimum": 0,
            "default": 0,
            "description": "Comparable per-execution price used by the ranking formula."
          },
          "latencyMs": {
            "type": "number",
            "minimum": 0,
            "default": 1000,
            "description": "Comparable latency in milliseconds."
          }
        },
        "additionalProperties": true
      },
      "description": "Provider candidates to rank. Unhealthy candidates are excluded."
    }
  },
  "required": [
    "providers"
  ],
  "description": "Rank a caller-supplied provider set. ARN does not discover providers or independently verify these metrics in this free call.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "selected": {
      "type": [
        "object",
        "null"
      ],
      "description": "Highest-ranked eligible provider, including its computed score, or null."
    },
    "alternates": {
      "type": "array",
      "maxItems": 3,
      "items": {
        "type": "object"
      },
      "description": "Up to three next-ranked eligible providers."
    },
    "reason": {
      "type": "string",
      "description": "Human-readable explanation of the routing result."
    }
  },
  "required": [
    "selected",
    "alternates",
    "reason"
  ],
  "additionalProperties": false
}
🟢json_normalize(value)

Recursively sort JSON object keys to produce stable structure and a deterministic JSON string. Use for comparisons, cache keys, repeatable payloads, or pre-signing preparation; do not use as RFC 8785/JCS canonicalization. This MCP call is read-only and does not charge: it returns the x402 endpoint and current price for execution.

输入模式

{
  "type": "object",
  "properties": {
    "value": {
      "description": "Any JSON value to normalize. Object keys are recursively sorted; array order and scalar values are preserved."
    }
  },
  "required": [
    "value"
  ],
  "description": "Input for deterministic JSON key-order normalization.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}
🟢object_contract_check(value, schema)

Check one JSON object's top-level required fields, allowed fields, and declared field types. Prefer this for new API/pipeline shape contracts; it is intentionally smaller and easier to reason about than full JSON Schema. This MCP call is read-only and returns x402 execution instructions without charging.

输入模式

{
  "type": "object",
  "properties": {
    "value": {
      "type": "object",
      "description": "JSON object to check."
    },
    "schema": {
      "type": "object",
      "description": "Top-level contract definition. Only required, properties.<field>.type, and additionalProperties=false are evaluated.",
      "properties": {
        "required": {
          "type": "array",
          "uniqueItems": true,
          "items": {
            "type": "string"
          },
          "description": "Top-level field names that must be present in value."
        },
        "properties": {
          "type": "object",
          "description": "Top-level field definitions. Each field may declare a JSON type; other JSON Schema keywords are ignored.",
          "additionalProperties": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "null",
                  "array",
                  "object",
                  "string",
                  "number",
                  "boolean"
                ],
                "description": "Expected JSON type for this top-level field."
              }
            },
            "additionalProperties": true
          }
        },
        "additionalProperties": {
          "type": "boolean",
          "description": "Set false to report top-level fields not declared in properties. Omitted or true allows them."
        }
      },
      "additionalProperties": true
    }
  },
  "required": [
    "value",
    "schema"
  ],
  "description": "Input for a fast top-level object-shape contract check.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}
🟢json_schema_check(value, schema)

Validate one JSON object when the caller already has a JSON-Schema-shaped contract. Only top-level required, properties.<field>.type, and additionalProperties=false are evaluated; for new simple contracts prefer object_contract_check. This MCP call is read-only and returns x402 execution instructions without charging.

输入模式

{
  "type": "object",
  "properties": {
    "value": {
      "type": "object",
      "description": "JSON object to validate against the supported schema subset."
    },
    "schema": {
      "type": "object",
      "description": "Top-level contract definition. Only required, properties.<field>.type, and additionalProperties=false are evaluated.",
      "properties": {
        "required": {
          "type": "array",
          "uniqueItems": true,
          "items": {
            "type": "string"
          },
          "description": "Top-level field names that must be present in value."
        },
        "properties": {
          "type": "object",
          "description": "Top-level field definitions. Each field may declare a JSON type; other JSON Schema keywords are ignored.",
          "additionalProperties": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "null",
                  "array",
                  "object",
                  "string",
                  "number",
                  "boolean"
                ],
                "description": "Expected JSON type for this top-level field."
              }
            },
            "additionalProperties": true
          }
        },
        "additionalProperties": {
          "type": "boolean",
          "description": "Set false to report top-level fields not declared in properties. Omitted or true allows them."
        }
      },
      "additionalProperties": true
    }
  },
  "required": [
    "value",
    "schema"
  ],
  "description": "Input for the bounded JSON-Schema-shaped compatibility checker.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}
🟢json_diff(before, after)

Produce a deterministic structural change list between two JSON values. Use for machine-readable change detection; arrays are compared by index and the result is capped at 1,000 changes, so this is not a JSON Patch generator. This MCP call is read-only and returns x402 execution instructions without charging.

输入模式

{
  "type": "object",
  "properties": {
    "before": {
      "description": "Original JSON value."
    },
    "after": {
      "description": "New JSON value to compare with before."
    }
  },
  "required": [
    "before",
    "after"
  ],
  "description": "Input for a deterministic structural comparison of two JSON values.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}
🟢dataset_profile(rows)

Profile 1-5,000 JSON-object rows for presence, missing/null counts, observed primitive types, primitive cardinality, and exact duplicate rows. Use for quick deterministic data-quality inspection, not statistical inference or schema validation. This MCP call is read-only and returns x402 execution instructions without charging.

输入模式

{
  "type": "object",
  "properties": {
    "rows": {
      "type": "array",
      "minItems": 1,
      "maxItems": 5000,
      "items": {
        "type": "object"
      },
      "description": "1-5,000 JSON objects. Rows are analyzed in memory and are not modified."
    }
  },
  "required": [
    "rows"
  ],
  "description": "Input for bounded profiling of a JSON-record dataset.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}
🟢verify_execution(candidate, checks)

Evaluate explicit boolean evidence across functional, security, privacy, copyright, regulatory, transaction-integrity, abuse, regression, and economics gates. Use after trusted verifiers have produced those booleans; this tool does not independently inspect code, systems, or legal compliance. This MCP call is read-only and returns x402 execution instructions without charging.

输入模式

{
  "type": "object",
  "properties": {
    "candidate": {
      "type": "object",
      "description": "Candidate metadata. candidate.id is returned when present; candidate contents are not independently inspected."
    },
    "checks": {
      "type": "object",
      "description": "Explicit boolean outcomes from trusted upstream verifiers. Every gate must be true to approve.",
      "required": [
        "functional",
        "security",
        "privacy",
        "copyright",
        "regulatory",
        "transactionIntegrity",
        "abuse",
        "regression",
        "economics"
      ],
      "properties": {
        "functional": {
          "type": "boolean",
          "description": "Functional acceptance checks passed."
        },
        "security": {
          "type": "boolean",
          "description": "Security checks passed."
        },
        "privacy": {
          "type": "boolean",
          "description": "Privacy checks passed."
        },
        "copyright": {
          "type": "boolean",
          "description": "Copyright/licensing checks passed."
        },
        "regulatory": {
          "type": "boolean",
          "description": "Applicable regulatory checks passed."
        },
        "transactionIntegrity": {
          "type": "boolean",
          "description": "Payment/transaction integrity checks passed."
        },
        "abuse": {
          "type": "boolean",
          "description": "Abuse and misuse checks passed."
        },
        "regression": {
          "type": "boolean",
          "description": "Regression checks passed."
        },
        "economics": {
          "type": "boolean",
          "description": "Economics gate passed."
        }
      },
      "additionalProperties": false
    }
  },
  "required": [
    "candidate",
    "checks"
  ],
  "description": "Input for evaluating previously computed execution-gate evidence.",
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "paymentRequired": {
      "type": "boolean",
      "const": true,
      "description": "Always true for paid ARN capabilities exposed over MCP."
    },
    "protocol": {
      "type": "string",
      "const": "x402",
      "description": "Payment protocol required by the HTTP execution endpoint."
    },
    "endpoint": {
      "type": "string",
      "description": "ARN HTTP path to POST the same tool arguments to for paid execution."
    },
    "price": {
      "type": "object",
      "required": [
        "amount",
        "asset",
        "network",
        "display"
      ],
      "properties": {
        "amount": {
          "type": "string",
          "description": "Atomic asset amount."
        },
        "asset": {
          "type": "string",
          "description": "Settlement asset."
        },
        "network": {
          "type": "string",
          "description": "CAIP-2 settlement network identifier."
        },
        "display": {
          "type": "string",
          "description": "Human-readable current price."
        }
      },
      "additionalProperties": false
    },
    "instruction": {
      "type": "string",
      "description": "How to execute the capability after receiving the payment requirement."
    }
  },
  "required": [
    "paymentRequired",
    "protocol",
    "endpoint",
    "price",
    "instruction"
  ],
  "description": "MCP payment instruction. Calling the MCP tool itself does not charge or execute the paid operation.",
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本8 个工具