Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
mcparmory avatar

Agentql

  • 29 repo stars
  • Updated May 12, 2026
  • mcparmory/registry

AgentQL is a MCP server that queries webpages with natural language and returns structured extracted data to agents.

About

AgentQL MCP lets coding agents query web pages in natural language and receive structured extractions instead of brittle CSS selectors. developers use it heavily during competitor and audience research: pricing tables, feature lists, changelog bullets, and positioning copy from sites that do not offer APIs. The server runs locally over stdio through uvx or Docker, which keeps credentials and browsing logic under your control compared with pure cloud scrape APIs. Package version 1.0.8 is published to PyPI and as an OCI image, so Claude Code, Cursor, and Windsurf-style setups can add it as a standard MCP dependency. Complexity is intermediate because you must phrase queries clearly and handle dynamic pages responsibly. Pair it with your own rate limits and robots/terms compliance; it automates reading the web, not strategic interpretation of what you collect.

  • 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

Agentql by the numbers

  • Data as of Jul 26, 2026 (Skillselion catalog sync)
terminal
claude mcp add mcparmory-agentql -- uvx mcparmory-agentql

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
repo stars29
Packagemcparmory-agentql
TransportSTDIO
AuthNone
Last updatedMay 12, 2026
Repositorymcparmory/registry

What it does

Extract structured fields from competitor and market web pages using natural-language queries inside the agent.

Who is it for?

Best when you're doing fast competitive teardowns and landing-page research without maintaining scrape scripts.

Skip if: Skip if you need authenticated in-app browser flows at scale or fully managed compliance-reviewed crawling only.

What you get

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

By the numbers

  • MCP package version 1.0.8
  • 2 distribution paths: PyPI uvx and OCI Docker
  • stdio transport only in published manifest
README.md

MCP Armory

MCP Armory Registry

Production-ready MCP servers for popular APIs, generated by MCP Blacksmith.

GitHub Stars License Servers Python 3.11+

Servers · Install & Usage · Features · How it works · License


MCP servers that connect AI agents to real-world APIs. Each server is a standalone Python package — generated from the upstream OpenAPI spec using MCP Blacksmith and tested against the live API before release. Hosted on MCP Armory or run independently.

Servers

🧠 AI & Machine LearningElevenLabs · Linkup · Parallel · Perplexity AI · Ragie · Replicate

📊 AnalyticsAhrefs · Datadog · Google Analytics · Google Search Console · Linkly · Mixpanel · PostHog

⛓️ Blockchain & CryptoAlchemy NFT

💼 CRM & SalesApollo

💬 CommunicationAtlassian Confluence · Google Gmail · MailerSend · Mailtrap · Postmark · Resend · Slack

🗄️ Data & DatabasesEnigma · Pinecone

🛠️ Developer ToolsAgentQL · Apify · Bitbucket · Bright Data · Browserbase · BuiltWith · Canvas · CircleCI · Codacy · Contentful Management · ConvertAPI · E2B · Firecrawl · GitHub · GitLab · LaunchDarkly · Postman · Scrapingant · Semrush AppCenter · Sentry

📄 Documents & PrintingPDF.co

🛒 E-commerceShopify Admin

💰 FinanceAlpha Vantage · Polygon · Ramp

👥 HR & RecruitingBambooHR

☁️ InfrastructureGlobalping · Grafana · PagerDuty · Rootly · Runpod

⚖️ Legal & ComplianceNetLicensing

🗺️ Maps & LocationGoogle Maps Platform · IP2Location.io IP Geolocation · OpenCage Geocoding

📣 MarketingCustomer.io Journeys Track · Klaviyo

🎬 Media & EntertainmentCanva · Perigon

ProductivityAirtable · Asana · Atlassian Jira · ClickUp · Figma · Google Sheets · Miro · Notion · Outline · Shortcut

🔍 SearchAlgolia Search · Google Search

📦 StorageBox · Files.com · Google Drive

📌 OtherClose

More servers are being added continuously.

Install & Usage

Every server is a standalone PyPI package (mcparmory-<server-name>). Each server's own README.md has full credential setup and configuration instructions.

# With uvx (no install needed)
uvx mcparmory-github

# With pip
pip install mcparmory-github
mcparmory-github

MCP client configuration (Claude Desktop, Cursor, Codex, Claude Code):

{
  "mcpServers": {
    "github": {
      "command": "uvx",
      "args": ["mcparmory-github"],
      "env": {
        "BEARER_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Features

Every server in this registry provides:

  • Full API coverage — all endpoints from the OpenAPI spec are exposed as MCP tools
  • Authentication — API key, Bearer token, Basic auth, OAuth2, JWT, OpenID Connect, and mutual TLS
  • Multi-auth — servers that support multiple auth methods let you configure whichever you prefer
  • Pydantic validation — request parameters are validated before sending to the API
  • Resilience — configurable retries with exponential backoff, connection pooling, and timeouts
  • Response sanitization — optional redaction of sensitive fields from API responses

How servers are generated

Servers are generated by MCP Blacksmith, an automated pipeline that:

  1. Parses an OpenAPI specification
  2. Transforms operations through LLM-driven passes (naming, parameter filtering, enhancement, classification)
  3. Generates a complete MCP server with auth, models, validation, and configuration
  4. Tests every tool against the live API using an autonomous agent
  5. Deploys passing servers to this registry

The generator targets Python 3.11+ and uses FastMCP as the MCP framework.

Contributing

Servers are auto-generated — don't edit server code directly. If you find an issue, open a GitHub Issue describing:

  • Broken or deprecated endpoints
  • Missing or incorrect parameters
  • Authentication problems
  • Incorrect request/response models

We'll re-generate the affected server with the fix. To request a new server, open an issue with a link to the API's OpenAPI spec or documentation.

License

Each generated server is released under the MIT License. The underlying APIs have their own terms of service — see individual server READMEs for details.


MCP Armory · MCP Blacksmith · Docs

Recommended MCP Servers

How it compares

Local NL web-extraction MCP, not a hosted equity database or ad-platform OAuth connector.

FAQ

Who is AgentQL for?

Developers 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.

Web & Browser Automationintegrationsfrontend

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.