Perceptlayer

Live web data for AI agents: structured JSON from 248 websites through one API key.

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
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

~672token 数(工具定义)
~1.0 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.53%)

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": {
    "web-data": {
      "url": "https://api.perceptlayer.com/mcp"
    }
  }
}

远程端点

https://api.perceptlayer.com/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_endpoints(query, vertical, limit)

Find Perceptlayer endpoints for a website or kind of data. The catalogue has 1659 endpoints across 248 sources, so search before calling. Query with the site and the data you want, e.g. "amazon product reviews", "airbnb listing", "linkedin company", "google maps places", "zillow property". Returns compact matches: endpoint ID (pass it to get_endpoint or call_endpoint), name, HTTP method, credits per call, tier ("restricted" endpoints need the account's restricted-endpoint terms accepted) and required parameters. Free; no API key needed.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Site and/or data wanted, in a few words, e.g. \"tripadvisor hotel reviews\"."
    },
    "vertical": {
      "type": "string",
      "enum": [
        "apps",
        "cars",
        "jobs",
        "marketplaces",
        "real-estate",
        "reviews",
        "search",
        "social",
        "travel",
        "web-seo"
      ],
      "description": "Optional: only return endpoints in this vertical."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "Maximum results (default 10)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢get_endpoint(endpoint)

Get the full parameter list for one endpoint: each parameter's name, type, whether it is required, allowed values and limits, plus an example set of parameters, the credit cost and tier. Call this before call_endpoint unless you already know the parameters. Free; no API key needed.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint": {
      "type": "string",
      "description": "Endpoint ID from search_endpoints, e.g. \"airbnb.listing\"."
    }
  },
  "required": [
    "endpoint"
  ],
  "additionalProperties": false
}
🟢call_endpoint(endpoint, params)

Run one endpoint and return its JSON response. Spends the endpoint's credits from the user's balance on success only; failed calls are free. Pass parameters exactly as get_endpoint lists them (array parameters as JSON arrays). The result reports credits used and remaining. Errors come back with a code: invalid_parameters (fix the parameters and retry), not_found (no data for these parameters), rate_limited or temporarily_unavailable (wait and retry), insufficient_credits, restricted_endpoint (the user must accept the restricted-endpoint terms in their dashboard), invalid_api_key (the MCP server config needs a valid API key). Responses over 100,000 characters are truncated; use paging or limit parameters to fetch less.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint": {
      "type": "string",
      "description": "Endpoint ID from search_endpoints, e.g. \"airbnb.listing\"."
    },
    "params": {
      "type": "object",
      "description": "Parameters for the endpoint, e.g. {\"listing_id\": \"18648717\"}.",
      "additionalProperties": true
    }
  },
  "required": [
    "endpoint"
  ],
  "additionalProperties": false
}

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