Skip to main content
Glama
enesjakozh
tinyfish-io

AgentQL MCP Server

by tinyfish-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

AgentQL MCP 服务器

这是一个集成了AgentQL数据提取功能的模型上下文协议 (MCP) 服务器。

特征

工具

  • extract-web-data - 从给定的“url”中提取结构化数据，使用“prompt”作为要提取的实际数据及其字段的描述。

Related MCP server: Fetcher MCP

安装

要使用 AgentQL MCP 服务器从网页中提取数据，您需要通过 npm 安装它，从我们的开发门户获取 API 密钥，然后在您最喜欢的支持 MCP 的应用程序中对其进行配置。

安装包

npm install -g agentql-mcp

配置 Claude

  • 通过⌘``,打开 Claude 桌面设置（不要与 Claude 帐户设置混淆）

  • 转到开发人员侧边栏部分

  • 单击**“编辑配置”**并打开claude_desktop_config.json文件

  • 在配置文件中的mcpServers字典中添加agentql服务器

  • 重启应用程序

{
  "mcpServers": {
    "agentql": {
      "command": "npx",
      "args": ["-y", "agentql-mcp"],
      "env": {
        "AGENTQL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

点击此处了解有关 Claude 中的 MCP 配置的更多信息。

配置光标

  • 打开游标设置

  • 前往MCP > MCP 服务器

  • 点击**+ 添加新的 MCP 服务器**

  • 输入以下内容：

    • 名称：“agentql”（或您喜欢的名称）

    • 类型：“命令”

    • 命令： env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp

在此处阅读有关 Cursor 中的 MCP 配置的更多信息。

配置 Windsurf

  • 打开Windsurf：MCP 配置面板

  • 点击添加自定义服务器+

  • 或者您可以直接打开~/.codeium/windsurf/mcp_config.json

  • 在配置文件中的mcpServers字典中添加agentql服务器

{
  "mcpServers": {
    "agentql": {
      "command": "npx",
      "args": ["-y", "agentql-mcp"],
      "env": {
        "AGENTQL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

在此处阅读有关 Windsurf 中 MCP 配置的更多信息。

验证 MCP 集成

给你的代理一个需要从网络中提取数据的任务。例如：

Extract the list of videos from the page https://www.youtube.com/results?search_query=agentql, every video should have a title, an author name, a number of views and a url to the video. Make sure to exclude ads items. Format this as a markdown table.

[!TIP] 如果您的代理抱怨它无法打开 URL 或从网络加载内容，而不是使用 AgentQL，请尝试添加“使用工具”或“使用 agentql 工具”提示。

发展

安装依赖项：

npm install

构建服务器：

npm run build

对于使用自动重建的开发：

npm run watch

如果您想尝试开发版本，您可以使用以下配置代替默认配置：

{
  "mcpServers": {
    "agentql": {
      "command": "/path/to/agentql-mcp/dist/index.js",
      "env": {
        "AGENTQL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

[!NOTE] 不要忘记删除默认的 AgentQL MCP 服务器配置，以免将 Claude 与两个类似的服务器混淆。

调试

由于 MCP 服务器通过 stdio 进行通信，调试起来可能比较困难。我们推荐使用MCP Inspector ，它以包脚本的形式提供：

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

Available Tools

1 tool
extract-web-dataA

Extracts structured data as JSON from a web page given a URL using a Natural Language description of the data.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL of the public webpage to extract data from
promptYesNatural Language description of the data to extract from the page

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Describes core function but omits important behavioral traits like rate limits, authentication requirements, handling of dynamic content, or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single concise sentence that is front-loaded and contains only essential information. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Mentions output format (JSON) but lacks details on return structure, error handling, or limitations like URL restrictions or page complexity. Adequate for a simple tool but incomplete for production use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. The description reinforces the 'prompt' parameter's nature but adds no new meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb (Extracts), resource (structured data as JSON from web page), and method (Natural Language description). Specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implicitly indicates use when needing structured data from a URL via NL description. No siblings to differentiate, but lacks explicit when-not-to-use or alternative methods.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Addedextract-web-data
  2. 1 tool updatev1.0.0
    • Removedextract-web-data
  3. 1 tool update
    • First observedextract-web-data
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A3.6/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no risk of confusion between tools, so disambiguation is perfect.

Naming Consistency5/5

The single tool name 'extract-web-data' follows a clear verb_noun pattern, and consistency is trivially maintained.

Tool Count2/5

A single tool is too few for a web scraping server, which typically requires tools for different actions (e.g., listing, configuring) or handling multiple extraction strategies.

Completeness2/5

The server only provides extraction via natural language, missing common features like pagination, multiple output formats, or error handling, leaving significant gaps for agents.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server Firecrawl

    Msparihar
    A
    license
    C
    quality
    D
    maintenance
    A server that provides web scraping and intelligent content searching capabilities using the Firecrawl API, enabling AI agents to extract structured data from websites and perform content searches.
    5
    3
    MIT

  • Fetcher MCP

    everford
    -
    license
    C
    quality
    Not graded
    maintenance
    A server that allows fetching web page content using Playwright headless browser with AI-powered capabilities for efficient information extraction.
    2
    4,375 npm
    7
    -

Appeared in Searches