# AgentQL MCP

Model Context Protocol server that exposes AgentQL data extraction capabilities to AI agents.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: high
- Recommended workflows: Browser automation, Coding agent workflow, Connector or protocol layer
- Permission surface: browser, memory, external services
- Agent JSON: https://www.openagent.bot/plugins/agentql-mcp.agent.json

## Summary
AgentQL MCP is an open-source Model Context Protocol server that integrates AgentQL's data extraction capabilities. It is relevant for agents that need structured web data extraction through an MCP-compatible tool surface.


## Guide
AgentQL MCP is an open-source Model Context Protocol server for AgentQL web data extraction.

### What it is
It gives AI agents an MCP-compatible tool surface for extracting structured data from web pages.

### Why it matters
Web agents become more useful when they can extract reliable structured data rather than only browse pages.

### How it works
Start with a non-sensitive page, configure the MCP server, and compare extracted data against the source before automating broader workflows.


### FAQ
- Is AgentQL MCP open source?
  - Yes. The GitHub repository is listed under the MIT license.
- Who should evaluate AgentQL MCP?
  - Teams building MCP tools for web extraction, browser agents, or research automation should evaluate it.
## What It Does
It gives AI agents an MCP-compatible tool surface for extracting structured data from web pages.

## How To Evaluate
Start with a non-sensitive page, configure the MCP server, and compare extracted data against the source before automating broader workflows.

## Why It Matters
Agents often need reliable data extraction from web pages, not just screenshots or raw HTML. AgentQL MCP packages that capability as an MCP server that compatible agent hosts can call.


## Best For
- Developers building web data extraction tools for agents
- Teams using MCP-compatible agent hosts
- Builders who need Playwright and AgentQL-style extraction in workflows

## Not For
- Teams that only need passive browsing
- Workflows where external web extraction is not allowed

## What It Actually Does
- MCP extraction tool: AgentQL MCP exposes data extraction as a Model Context Protocol server.
  - Why it matters: MCP makes extraction reusable across compatible agent environments.
- AgentQL integration: The server integrates AgentQL's data extraction capabilities.
  - Why it matters: Structured extraction helps agents work with web data more reliably than raw page text.
- Web automation fit: Repository topics include Playwright, scraping, Cursor, Claude, and MCP.
  - Why it matters: The project sits directly in the browser-agent and web-tooling stack.

## Typical Use Cases
- Web data extraction: Expose structured web extraction to an MCP-compatible assistant.
- Browser-agent tools: Pair with browser workflows where agents need data, not only page navigation.
- Research automation: Extract structured information from web pages before synthesis.

## How It Compares
- When to choose AgentQL MCP: Compare it with nearby plugins by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Browser automation: strong. AgentQL MCP has multiple signals for browser automation, including matching tags, capabilities, category, or positioning. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Coding agent workflow: strong. AgentQL MCP has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: strong. AgentQL MCP has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Memory or RAG workflow: partial. AgentQL MCP has at least one signal for memory or rag workflow, but should be checked against a real task before adoption. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Reusable skill workflow: partial. AgentQL MCP has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Evaluation and observability: weak. AgentQL MCP is not primarily positioned for evaluation and observability in the current metadata. Required check: Add one repeatable test case and confirm results can run again in review or CI.

## Evidence
- verified: AgentQL MCP is listed as open source. Source: License metadata: MIT
- verified: AgentQL MCP has a recorded GitHub repository: tinyfish-io/agentql-mcp. Source: Resource facts and GitHub source link.
- inferred: AgentQL MCP supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: AgentQL MCP is tagged with plugin, mcp, protocol, connectors, browser automation capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/tinyfish-io/agentql-mcp
- Open Homepage: https://docs.agentql.com/integrations/mcp

## Facts
- Category: plugins
- Resource type: plugin
- Open source: yes
- License: MIT
- Last verified: 2026-06-11
- GitHub repo: tinyfish-io/agentql-mcp
- GitHub stars: 174

## Capabilities
- plugin
- mcp
- protocol
- connectors
- browser-automation

## Structured Use Case Tags
- browser-agent
- developer-workflow

## Getting Started
- Open the GitHub repository: https://github.com/tinyfish-io/agentql-mcp
- Read the integration docs: https://docs.agentql.com/integrations/mcp

## Links
- GitHub: https://github.com/tinyfish-io/agentql-mcp
- Homepage: https://docs.agentql.com/integrations/mcp

## Structured Outputs
- JSON: https://www.openagent.bot/plugins/agentql-mcp.json
- Markdown: https://www.openagent.bot/plugins/agentql-mcp.md
- Agent JSON: https://www.openagent.bot/plugins/agentql-mcp.agent.json
- Canonical: https://www.openagent.bot/plugins/agentql-mcp