Skip to content
Back to search

agentql-mcp

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/tinyfish-io/agentql-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/tinyfish-io/agentql-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tinyfish-io--agentql-mcp/badge.svg)](/listings/tinyfish-io--agentql-mcp)

HTML

<a href="/listings/tinyfish-io--agentql-mcp"><img src="/api/listings/tinyfish-io--agentql-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

To use AgentQL MCP Server to extract data from web pages, you need to install it via npm, get an API key from our [Dev Portal](https://dev.agentql.com), and configure it in your favorite app that supports MCP.

Install the package

npm install -g agentql-mcp

Configure Claude

- Open Claude Desktop **Settings** via `⌘`+`,` (don't confuse with Claude Account Settings) - Go to **Developer** sidebar section - Click **Edit Config** and open `claude_desktop_config.json` file - Add `agentql` server inside `mcpServers` dictionary in the config file - Restart the app

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

Read more about MCP configuration in Claude [here](https://modelcontextprotocol.io/quickstart/user).

Configure VS Code

For one-click installation, click one of the install buttons below:

Manual Installation

Click the install buttons at the top of this section for the quickest installation method. For manual installation, follow these steps:

Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing `Ctrl + Shift + P` and typing `Preferences: Open User Settings (JSON)`.

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "apiKey",
        "description": "AgentQL API Key",
        "password": true
      }
    ],
    "servers": {
      "agentql": {
        "command": "npx",
        "args": ["-y", "agentql-mcp"],
        "env": {
          "AGENTQL_API_KEY": "${input:apiKey}"
        }
      }
    }
  }
}

Optionally, you can add it to a file called `.vscode/mcp.json` in your workspace. This will allow you to share the configuration with others.

{
  "inputs": [
    {
      "type": "promptString",
      "id": "apiKey",
      "description": "AgentQL API Key",
      "password": true
    }
  ],
  "servers": {
    "agentql": {
      "command": "npx",
      "args": ["-y", "agentql-mcp"],
      "env": {
        "AGENTQL_API_KEY": "${input:apiKey}"
      }
    }
  }
}

Configure Cursor

- Open **Cursor Settings** - Go to **MCP > MCP Servers** - Click **+ Add new MCP Server** - Enter the following: - Name: "agentql" (or your preferred name) - Type: "command" - Command: `env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp`

Read more about MCP configuration in Cursor [here](https://docs.cursor.com/context/model-context-protocol).

Configure Windsurf

- Open **Windsurf: MCP Configuration Panel** - Click **Add custom server+** - Alternatively you can open `~/.codeium/windsurf/mcp_config.json` directly - Add `agentql` server inside `mcpServers` dictionary in the config file

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

Read more about MCP configuration in Windsurf [here](https://docs.codeium.com/windsurf/mcp).

Validate MCP integration

Give your agent a task that will require extracting data from the web. For example:

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] > In case your agent complains that it can't open urls or load content from the web instead of using AgentQL, try adding "use tools" or "use agentql tool" hint.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 197 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # AgentQL MCP Server
  2. This is a Model Context Protocol (MCP) server that integrates [AgentQL](https://agentql.com)'s data extraction capabilities.
  3. ## Features
  4. ### Tools
  5. - `extract-web-data` - extract structured data from a given 'url', using 'prompt' as a description of actual data and its fields to extract.
  6. ## Installation
  7. To use AgentQL MCP Server to extract data from web pages, you need to install it via npm, get an API key from our [Dev Portal](https://dev.agentql.com), and configure it in your favorite app that supports MCP.
  8. ### Install the package
  9. ```bash
  10. npm install -g agentql-mcp
  11. ```
  12. ### Configure Claude
  13. - Open Claude Desktop **Settings** via `⌘`+`,` (don't confuse with Claude Account Settings)
  14. - Go to **Developer** sidebar section
  15. - Click **Edit Config** and open `claude_desktop_config.json` file
  16. - Add `agentql` server inside `mcpServers` dictionary in the config file
  17. - Restart the app
  18. ```json title="claude_desktop_config.json"
  19. {
  20. "mcpServers": {
  21. "agentql": {
  22. "command": "npx",
  23. "args": ["-y", "agentql-mcp"],
  24. "env": {
  25. "AGENTQL_API_KEY": "YOUR_API_KEY"
  26. }
  27. }
  28. }
  29. }
  30. ```
  31. Read more about MCP configuration in Claude [here](https://modelcontextprotocol.io/quickstart/user).
  32. ### Configure VS Code
  33. For one-click installation, click one of the install buttons below:
  34. [![Install with NPX in VS Code](https://img.shields.io/badge/VS_Code-NPM-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=agentql&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22agentql-mcp%22%5D%2C%22env%22%3A%7B%22AGENTQL_API_KEY%22%3A%22%24%7Binput%3AapiKey%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22apiKey%22%2C%22description%22%3A%22AgentQL+API+Key%22%2C%22password%22%3Atrue%7D%5D) [![Install with NPX in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-NPM-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=agentql&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22agentql-mcp%22%5D%2C%22env%22%3A%7B%22AGENTQL_API_KEY%22%3A%22%24%7Binput%3AapiKey%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22apiKey%22%2C%22description%22%3A%22AgentQL+API+Key%22%2C%22password%22%3Atrue%7D%5D&quality=insiders)
  35. #### Manual Installation
  36. Click the install buttons at the top of this section for the quickest installation method. For manual installation, follow these steps:
  37. Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing `Ctrl + Shift + P` and typing `Preferences: Open User Settings (JSON)`.
  38. ```json
  39. {
  40. "mcp": {
  41. "inputs": [
  42. {
  43. "type": "promptString",
  44. "id": "apiKey",
  45. "description": "AgentQL API Key",
  46. "password": true
  47. }
  48. ],
  49. "servers": {
  50. "agentql": {
  51. "command": "npx",
  52. "args": ["-y", "agentql-mcp"],
  53. "env": {
  54. "AGENTQL_API_KEY": "${input:apiKey}"
  55. }
  56. }
  57. }
  58. }
  59. }
  60. ```
  61. Optionally, you can add it to a file called `.vscode/mcp.json` in your workspace. This will allow you to share the configuration with others.
  62. ```json
  63. {
  64. "inputs": [
  65. {
  66. "type": "promptString",
  67. "id": "apiKey",
  68. "description": "AgentQL API Key",
  69. "password": true
  70. }
  71. ],
  72. "servers": {
  73. "agentql": {
  74. "command": "npx",
  75. "args": ["-y", "agentql-mcp"],
  76. "env": {
  77. "AGENTQL_API_KEY": "${input:apiKey}"
  78. }
  79. }
  80. }
  81. }
  82. ```
  83. ### Configure Cursor
  84. - Open **Cursor Settings**
  85. - Go to **MCP > MCP Servers**
  86. - Click **+ Add new MCP Server**
  87. - Enter the following:
  88. - Name: "agentql" (or your preferred name)
  89. - Type: "command"
  90. - Command: `env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp`
  91. Read more about MCP configuration in Cursor [here](https://docs.cursor.com/context/model-context-protocol).
  92. ### Configure Windsurf
  93. - Open **Windsurf: MCP Configuration Panel**
  94. - Click **Add custom server+**
  95. - Alternatively you can open `~/.codeium/windsurf/mcp_config.json` directly
  96. - Add `agentql` server inside `mcpServers` dictionary in the config file
  97. ```json title="mcp_config.json"
  98. {
  99. "mcpServers": {
  100. "agentql": {
  101. "command": "npx",
  102. "args": ["-y", "agentql-mcp"],
  103. "env": {
  104. "AGENTQL_API_KEY": "YOUR_API_KEY"
  105. }
  106. }
  107. }
  108. }
  109. ```
  110. Read more about MCP configuration in Windsurf [here](https://docs.codeium.com/windsurf/mcp).
  111. ### Validate MCP integration
  112. Give your agent a task that will require extracting data from the web. For example:
  113. ```text
  114. 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.
  115. ```
  116. > [!TIP]
  117. > In case your agent complains that it can't open urls or load content from the web instead of using AgentQL, try adding "use tools" or "use agentql tool" hint.
  118. ## Development
  119. Install dependencies:
  120. ```bash
  121. npm install
  122. ```
  123. Build the server:
  124. ```bash
  125. npm run build
  126. ```
  127. For development with auto-rebuild:
  128. ```bash
  129. npm run watch
  130. ```
  131. If you want to try out development version, you can use the following config instead of the default one:
  132. ```json
  133. {
  134. "mcpServers": {
  135. "agentql": {
  136. "command": "/path/to/agentql-mcp/dist/index.js",
  137. "env": {
  138. "AGENTQL_API_KEY": "YOUR_API_KEY"
  139. }
  140. }
  141. }
  142. }
  143. ```
  144. > [!NOTE]
  145. > Don't forget to remove the default AgentQL MCP server config to not confuse Claude with two similar servers.
  146. ## Debugging
  147. Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:
  148. ```bash
  149. npm run inspector
  150. ```
  151. The Inspector will provide a URL to access debugging tools in your browser.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.