AgentQL MCP
Extracts structured data from any web page using AgentQL's natural-language element queries.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for AgentQL MCP, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
AgentQL MCP lets an agent point at a URL and describe the data it wants; AgentQL resolves that to page elements and returns structured JSON, resilient to layout changes. Tool surface centers on an extract-data tool backed by the AgentQL API key. Security surface: fetches arbitrary pages and returns their content to the model, so untrusted page text can carry injected instructions.
Key features and capabilities
- Natural-language queries mapped to DOM elements
- Structured JSON output resilient to markup changes
- Works across arbitrary public web pages
Use cases
- Scrape product/listing data without brittle selectors
- Turn web pages into typed data for agents