# AgentQL

> Use this tool when you need to extract structured data from web pages without custom scraping, and integrate it into AI workflows. AgentQL accepts a URL and natural language prompt as input, and outputs relevant data in JSON format. It solves data extraction problems for AI assistants, providing on-demand access to specific web content information.

Canonical page: https://skillsregistry.net/skills/tinyfish-agentql  
JSON: https://api.skillsregistry.net/v1/skills/tinyfish-agentql

## Description

AgentQL MCP server integrates with the AgentQL data extraction API to provide AI assistants with structured data extraction capabilities from web pages. The server exposes a single tool that accepts a URL and natural language prompt, then uses the AgentQL API to extract relevant data in JSON format based on the description. This implementation is particularly useful for scenarios requiring structured data from websites without needing to write custom scrapers, enabling AI assistants to gather specific information from web content on demand.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/tinyfish-agentql)
- **Repository:** <https://github.com/tinyfish-io/agentql-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "tinyfish-agentql"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tinyfish-agentql` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tinyfish-agentql/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt