Skip to main content

WebQuest MCP is a Model Context Protocol (MCP) server that exposes powerful web search and scraping tools to AI agents and MCP-compatible clients.

Project description

WebQuest MCP

WebQuest MCP is a Model Context Protocol (MCP) server that exposes powerful web search and scraping tools to AI agents and MCP-compatible clients.

Scrapers

  • Any Article: Extracts readable content from arbitrary web articles.
  • DuckDuckGo Search: General web search using DuckDuckGo.
  • Google News Search: News-focused search via Google News.
  • YouTube Search: Search YouTube videos, channels, posts, and shorts.
  • YouTube Transcript: Fetch transcripts for YouTube videos.

Browsers

  • Hyperbrowser: A cloud-based browser service for running Playwright scrapers without managing infrastructure.

Installation

Installing using pip:

pip install webquest-mcp

Installing using uv:

uv add webquest-mcp

Usage

Starting the server

To start the WebQuest MCP server, run:

webquest-mcp

This will launch the MCP server using the streamable-http transport. The server will listen for incoming connections from MCP-compatible clients (like Cursor, Windsurf, or other AI agents).

Configuration

You can configure the server using either environment variables (recommended) or command-line arguments.

Environment variables

Create a .env file in your working directory with the following content:

# Required API keys
OPENAI_API_KEY=your_openai_api_key
HYPERBROWSER_API_KEY=your_hyperbrowser_api_key

# Optional authentication (JWT)
AUTH_SECRET=your_jwt_secret_key
AUTH_AUDIENCE=webquest-mcp

Command-line arguments

Alternatively, you can pass configuration options directly when running the server:

webquest-mcp --openai_api_key "..." --hyperbrowser_api_key "..."

To see all available options, run:

webquest-mcp --help

Token generation

To generate an authentication token for the MCP client, use the webquest-mcp-token command. You need to provide a secret and a subject.

webquest-mcp-token --auth_secret "your-secret-key" --auth_subject "client-name"

You can also configure these values using environment variables or a .env file.

Disclaimer

This tool is for educational and research purposes only. The developers of WebQuest MCP are not responsible for any misuse of this tool. Scraping websites may violate their Terms of Service. Users are solely responsible for ensuring their activities comply with all applicable laws and website policies.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

webquest_mcp-0.4.0.tar.gz (3.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

webquest_mcp-0.4.0-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file webquest_mcp-0.4.0.tar.gz.

File metadata

  • Download URL: webquest_mcp-0.4.0.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.9.1

File hashes

Hashes for webquest_mcp-0.4.0.tar.gz
Algorithm Hash digest
SHA256 c17cb6ec2e685347348300f1d5d7f59582163c5b0e88c164418710d7a06eb0e6
MD5 b18d733370a21596714cfbacd02a28d4
BLAKE2b-256 fa8cb67160f51bc7f5db61cfe11f5f61421f33a836c6809bdd36299c63e31e03

See more details on using hashes here.

File details

Details for the file webquest_mcp-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for webquest_mcp-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 79e605c900fda4ed16da9b29a658da57da99a98ff9e6cdac0b4f8c0c8ee02519
MD5 ba72d06193e7187a7fc20edd9aa7a3b9
BLAKE2b-256 581201d4cbf4a84cf04488768203b46b8bb95740259e93e4eb49cb48b01312e8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page