Agentql
Extract structured fields from competitor and market web pages using natural-language queries inside the agent.
Overview
AgentQL is a MCP server for the Idea phase that queries webpages with natural language and returns structured extracted data to agents.
What is this MCP server?
- Natural-language queries against webpages for structured data
- stdio MCP via uvx (PyPI mcparmory-agentql) or Docker ghcr.io/mcparmory/agentql
- Version 1.0.8 with dual PyPI and OCI distribution
- suited for ad-hoc site intelligence without custom scrapers
- GitHub source under mcparmory/registry
- MCP package version 1.0.8
- 2 distribution paths: PyPI uvx and OCI Docker
- stdio transport only in published manifest
Community signal: 25 GitHub stars.
What problem does it solve?
Competitor and market pages are messy HTML, and writing one-off scrapers for every validation sprint burns solo-builder time.
Who is it for?
Indie founders doing fast competitive teardowns and landing-page research without maintaining scrape scripts.
Skip if: Teams that need authenticated in-app browser flows at scale or fully managed compliance-reviewed crawling only.
What do I get? / Deliverables
Your agent issues NL queries against URLs and gets structured fields you can drop into comparison tables or specs.
- Structured JSON-like field sets from queried pages
- Reusable NL queries instead of per-site scraper code
- Local stdio MCP integration for research workflows
Recommended MCP Servers
Journey fit
Canonical shelf is Idea because builders most often deploy AgentQL to harvest competitor pricing, features, and positioning from live sites during discovery. Competitors subphase fits repeatable extraction from arbitrary URLs when you lack a clean public API.
How it compares
Local NL web-extraction MCP, not a hosted equity database or ad-platform OAuth connector.
Common Questions / FAQ
Who is AgentQL for?
Builders and agents users who want natural-language webpage queries and structured output during research and integration prototyping.
When should I use AgentQL?
Use it when validating ideas or mapping competitors and you need repeatable extractions from public web pages.
How do I add AgentQL to my agent?
Add stdio MCP using uvx mcparmory-agentql 1.0.8 or the Docker image ghcr.io/mcparmory/agentql:1.0.8 in your MCP config.