SignalHarness.ai

330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
77%
命名质量
100%
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

~941token 数(工具定义)
~2.6 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.74%)

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": {
    "mcp": {
      "url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}

远程端点

https://signalharness.ai/api/agent/services/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_services

Discover the currently enabled public SignalHarness service catalog before choosing a service. This free, read-only call takes no arguments and returns a compact service array with canonical IDs, descriptions, prices, and supported payment metadata. Results follow the canonical catalog order; compare services by their exact service_id.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schemaVersion": {
      "description": "Catalog schema version when supplied by the runtime."
    },
    "services": {
      "type": "array",
      "description": "Enabled public services in canonical catalog order. Each item includes its exact service ID and available discovery and payment fields.",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "error": {
      "type": "string",
      "description": "Stable machine error code when catalog discovery fails."
    }
  },
  "description": "A compact public catalog response, or a normalized machine-readable error.",
  "additionalProperties": true
}
🟢get_service(service_id)

Inspect one enabled public SignalHarness service before invoking it. Use an exact service_id returned by list_services. This free, read-only call returns the canonical description, input and output schemas, price, endpoint, and supported payment metadata when available; an unknown or disabled ID returns a normalized not-found error.

输入模式

{
  "type": "object",
  "properties": {
    "service_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]{0,159}$",
      "description": "Exact canonical service ID from list_services; matching is case-sensitive and aliases are not accepted."
    }
  },
  "required": [
    "service_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "service_id": {
      "type": "string",
      "description": "Exact canonical service ID."
    },
    "input_schema": {
      "type": "object",
      "description": "JSON Schema the invoke_service input must satisfy."
    },
    "output_schema": {
      "type": "object",
      "description": "JSON Schema describing the service-specific success result."
    },
    "error": {
      "type": "string",
      "description": "Stable machine error code when the service cannot be returned."
    }
  },
  "description": "Canonical public service metadata, or a normalized machine-readable error.",
  "additionalProperties": true
}
🟢invoke_service(service_id, input, request_id, idempotency_key)

Run exactly one enabled public SignalHarness service with caller-supplied input. Call get_service first and validate input against its input_schema. An unpaid call returns the canonical x402 V2 PAYMENT-REQUIRED challenge plus the equivalent x402 V1 JSON challenge; a client can then retry once with payment in params._meta["x402/payment"]. The server never retries automatically. A paid call may settle the advertised charge and perform external work, then returns service-specific structured JSON or a normalized error.

输入模式

{
  "type": "object",
  "properties": {
    "service_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]{0,159}$",
      "description": "Exact canonical ID of an enabled public service, obtained from list_services."
    },
    "input": {
      "type": "object",
      "description": "Caller-supplied job data. It must satisfy the selected service input_schema returned by get_service."
    },
    "request_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]{0,159}$",
      "description": "Optional caller-generated request identifier for tracing this attempt. Never place secrets or payment credentials in it."
    },
    "idempotency_key": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]{0,159}$",
      "description": "Optional stable key for retrying the same logical job safely. Reuse it only for recovery of that same job and payment."
    }
  },
  "required": [
    "service_id",
    "input"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "error": {
      "type": "string",
      "description": "Stable machine error code for unpaid, invalid, failed, or unavailable requests."
    }
  },
  "description": "Service-specific structured JSON, an unpaid x402 challenge, or a normalized machine-readable error. Inspect get_service.output_schema for the selected service success shape.",
  "additionalProperties": true
}

推荐提示词

retrieve_data
Get details about [item] from SignalHarness.ai
预期工具: get_service
fetch_info
Fetch [information type] using SignalHarness.ai
预期工具: get_service
list_items
List all [items] available in SignalHarness.ai
预期工具: list_services
browse_collection
Show me the [collection] from SignalHarness.ai
预期工具: list_services
explore_workflow
List available [items], then get details for each one using SignalHarness.ai
预期工具: list_servicesget_service

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具
已验证未记录版本3 个工具