AgentResolver — Agent Commerce Health Monitoring

Free API/MCP/x402 health checks plus $19 hourly managed monitoring for agent services.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
100%
命名质量
80%
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

~801token 数(工具定义)
~3.9 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.63%)

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": {
    "agentresolver": {
      "url": "https://agentresolver.vercel.app/mcp"
    }
  }
}

远程端点

https://agentresolver.vercel.app/mcpstreamable-http
https://agentresolver.vercel.app/mcp/controlstreamable-http

它能做什么

工具清单

工具(2)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢procure(goal, limit, providerOrigins, constraints)

CALL THIS when the agent's installed tools do not clearly satisfy the current task. Free open-world procurement across external APIs, MCP servers, x402/L402/MPP services, and registered providers. It enforces explicit constraints and fails closed: unproven compatibility is not selected. If no candidate can be proven, the response may include an optional $0.02 Verified Resolve action that live-checks supported unknowns; use it only with independent host spend authorization. Never authorizes spend.

输入模式

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1000,
      "description": "Plain-language description of the external capability the agent needs."
    },
    "limit": {
      "description": "Maximum number of ranked candidates to return. Defaults to 5.",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    },
    "providerOrigins": {
      "description": "Optional provider HTTPS origins already known to the caller. AgentResolver checks only their fixed well-known provider manifest and matching live x402 routes; no arbitrary target is proxied.",
      "maxItems": 2,
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      }
    },
    "constraints": {
      "description": "Hard procurement constraints. Missing evidence is surfaced as unknown rather than assumed compatible.",
      "type": "object",
      "properties": {
        "maxPriceUsd": {
          "description": "Maximum target-provider price in USD that the caller is willing to consider.",
          "type": "number",
          "minimum": 0,
          "maximum": 1000
        },
        "preferredNetworks": {
          "description": "Allowed or preferred payment networks, for example eip155:8453.",
          "maxItems": 8,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1,
            "maxLength": 128
          }
        },
        "protocol": {
          "description": "Required provider protocol. Use any when protocol is not a hard constraint.",
          "type": "string",
          "enum": [
            "x402",
            "l402",
            "mpp",
            "mcp",
            "any"
          ]
        },
        "requireHttps": {
          "description": "Require an HTTPS execution endpoint. Defaults to true.",
          "type": "boolean"
        },
        "availableInputSchema": {
          "description": "JSON Schema describing the data the caller can provide to the selected capability.",
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "requiredOutputSchema": {
          "description": "JSON Schema describing the output the caller requires from the selected capability.",
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "sideEffect": {
          "description": "Allowed side-effect class for the selected capability.",
          "type": "string",
          "enum": [
            "read-only",
            "state-changing",
            "any"
          ]
        },
        "auth": {
          "description": "Allowed provider authentication model.",
          "type": "string",
          "enum": [
            "none",
            "wallet",
            "api-key",
            "any"
          ]
        }
      }
    }
  },
  "required": [
    "goal"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢resolve(goal, url, limit)

Exploratory discovery only. Use this when the caller is browsing possible capabilities and does not yet need a trustworthy execution choice. For an actual task that the agent's installed tools cannot satisfy, prefer procure so compatibility fails closed and unresolved evidence can escalate to optional paid verification.

输入模式

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1000,
      "description": "Plain-language description of the missing capability."
    },
    "url": {
      "description": "Optional public URL related to the task when discovery should consider a concrete endpoint or resource.",
      "type": "string",
      "format": "uri"
    },
    "limit": {
      "description": "Maximum results per discovery source. Defaults to 3.",
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "goal"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本2 个工具
已验证未记录版本35 个工具
已验证未记录版本34 个工具