https://github.com/tinyfish-io/agentql-mcp
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
https://github.com/tinyfish-io/agentql-mcp
agent agentql ai aiagent claude cursor llm-tools mcp mcp-server model-context-protocol playwright scraping web web-scraping web-scrapping webagent windsurf
Last synced: 23 days ago
JSON representation
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
- Host: GitHub
- URL: https://github.com/tinyfish-io/agentql-mcp
- Owner: tinyfish-io
- License: mit
- Created: 2024-12-21T01:12:55.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-03-13T15:39:44.000Z (about 1 month ago)
- Last Synced: 2025-03-13T16:37:16.000Z (about 1 month ago)
- Topics: agent, agentql, ai, aiagent, claude, cursor, llm-tools, mcp, mcp-server, model-context-protocol, playwright, scraping, web, web-scraping, web-scrapping, webagent, windsurf
- Language: JavaScript
- Homepage: https://docs.agentql.com/integrations/mcp
- Size: 536 KB
- Stars: 0
- Watchers: 7
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
- awesome-mcp-zh - AgentQL
- Awesome-MCP-Servers-directory - AgentQL - Enable AI agents to get structured data from unstructured web (AI Services)
- awesome-mcp-servers - AgentQL MCP - Model Context Protocol server that integrates AgentQL's data extraction capabilities. (Table of Contents / Other Tools and Integrations)
- awesome-mcp-servers - AgentQL MCP - Model Context Protocol server that integrates AgentQL's data extraction capabilities. (Table of Contents / Other Tools and Integrations)
- awesome-mcp-servers - AgentQL - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). (Official Servers)
README
# AgentQL MCP Server
This is a Model Context Protocol (MCP) server that integrates [AgentQL](https://agentql.com)'s data extraction capabilities.
## Features
### Tools
- `extract-web-data` - extract structured data from a given 'url', using 'prompt' as a description of actual data and its fields to extract.
## Installation
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
```bash
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
```json title="claude_desktop_config.json"
{
"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 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
```json title="mcp_config.json"
{
"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:
```text
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.
## Development
Install dependencies:
```bash
npm install
```
Build the server:
```bash
npm run build
```
For development with auto-rebuild:
```bash
npm run watch
```
If you want to try out development version, you can use the following config instead of the default one:
```json
{
"mcpServers": {
"agentql": {
"command": "/path/to/agentql-mcp/dist/index.js",
"env": {
"AGENTQL_API_KEY": "YOUR_API_KEY"
}
}
}
}
```
> [!NOTE]
> Don't forget to remove the default AgentQL MCP server config to not confuse Claude with two similar servers.
## Debugging
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:
```bash
npm run inspector
```
The Inspector will provide a URL to access debugging tools in your browser.