agentql
The agentql server provides tools to extract structured data from webpages, manage browser sessions, and monitor API usage.
Extract structured data from webpages (
query_webpage_data): Query live URLs or raw HTML using AgentQL query syntax or natural language prompts, with support for dynamic content loading, proxy routing, screenshots, lazy-load scrolling, and configurable browser profiles (light, stealth, tf-browser).Monitor API usage (
get_usage): Retrieve current API key usage statistics and subscription/quota details for the authenticated account.Create browser sessions (
create_browser_session): Spin up a new Tetra browser session with customizable user agent, browser profile, proxy settings, and lifecycle/shutdown behavior (idle timeout or on-disconnect).List browser session usage (
list_session_usage): Retrieve a paginated, filterable history of Tetra browser session usage records, with filters for session ID, sub-user, status (running/ended), and time range.
AgentQL MCP Server
Base URL: https://api.agentql.com
Category | Developer Tools |
Tools | 3 |
Auth | API Key |
Install
Quick Start (recommended)
API_KEY=YOUR_API_KEY \
uvx mcparmory-agentqlWith pip
pip install mcparmory-agentql
API_KEY=YOUR_API_KEY \
mcparmory-agentqlMCP Client Configuration
Add to your MCP client config (e.g. Claude Desktop, Cursor, Codex):
{
"mcpServers": {
"agentql": {
"command": "uvx",
"args": ["mcparmory-agentql"],
"env": {
"API_KEY": "YOUR_API_KEY"
}
}
}
}Related MCP server: Hyperbrowser MCP Server
Credentials
Set the following environment variables (via MCP client env config, shell export, or .env file):
API_KEY— API Key Authentication (X-API-Key)
Do not commit credentials to version control.
Run Locally
First, configure your credentials in .env (see Credentials above).
pip install -r requirements.txt
python server.pyConnect MCP Client
Edit .mcp.json and replace <SERVER_DIR> with the absolute path to this directory, then add to your MCP client configuration.
Example (if server is at /home/user/mcp-servers/agentql):
{
"mcpServers": {
"agentql": {
"command": "python",
"args": ["/home/user/mcp-servers/agentql/server.py"]
}
}
}Docker
Pre-built image (recommended)
docker run -p 8000:8000 \
-e API_KEY=YOUR_API_KEY \
ghcr.io/mcparmory/agentql:latestBuild from source
First, configure your credentials in .env (see Credentials above).
docker build -t agentql .
docker run -p 8000:8000 --env-file .env agentqlBefore running, make sure ports 8000 are free.### MCP client config (Docker)
For Docker, use SSE transport in your MCP client config:
{
"mcpServers": {
"agentql": {
"type": "sse",
"url": "http://localhost:8000/sse"
}
}
}Files
.env- Credentials and server configuration.mcp.json- MCP client config templateDockerfile- Container buildLICENSE- MIT license for this generated coderequirements.txt- Python dependenciesREADME.md- This fileserver.py- MCP server entry point_auth.py- Authentication handlers_models.py- Request/response models_validators.py- Input validation
Note: Files starting with . are hidden by default on macOS/Linux. Use ls -a in terminal or enable "Show hidden files" in your file manager to see .env and .mcp.json.
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceProvides browser automation and web scraping capabilities including page navigation, form filling, data extraction, and intelligent conversion of web pages to Markdown format.Last updated1
- Alicense-quality-maintenanceProvides tools to scrape, extract structured data, and crawl webpages, with access to browser automation agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use for complex web tasks.Last updated
- Alicense-qualityDmaintenanceProvides browser automation capabilities using Playwright, enabling users to navigate websites, extract content, take screenshots, and interact with web pages through natural language prompts.Last updated24MIT
- Alicense-qualityDmaintenanceEnables browser automation and web scraping with multi-session management, supporting page navigation, element interaction, network request capture, and content extraction across multiple concurrent browser instances.Last updated3MIT
Related MCP Connectors
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Automate cloud browsers to navigate websites, interact with elements, and extract structured data.…
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mcparmory/registry'
If you have feedback or need assistance with the MCP directory API, please join our Discord server