Getweb

Provides web search and content extraction capabilities via MCP endpoints.
  • javascript

13

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "ivan-mezentsev-mcp-getweb": {
      "command": "npx",
      "args": [
        "mcp-getweb"
      ],
      "env": {
        "JINA_API_KEY": "YOUR_JINA_API_KEY",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
        "GOOGLE_SEARCH_ENGINE_ID": "YOUR_SEARCH_ENGINE_ID"
      }
    }
  }
}

You deploy an MCP Server that provides web search and content extraction capabilities, enabling you to perform searches, fetch web content, and extract useful metadata efficiently from a single, consistent interface.

How to use

You interact with the MCP GetWeb server through an MCP client. The server exposes several search and content tools that you can leverage to search the web, fetch page content, extract metadata, and convert pages to usable formats. Use the available tools to gather information, analyze sources, and present results in your application or workflow.

  • DuckDuckGo Search for HTML-scraped results
  • Google Search via Programmable Search for targeted results
  • Felo AI Search for up-to-date, context-aware prompts
  • Fetch URL to grab clean page content
  • URL Metadata Extractor for title/description/image/favicon
  • URL Fetch to Markdown for easy rendering
  • Jina Reader for structured, concise content from a URL

How to install

Follow these steps to install and run the MCP GetWeb server locally.

{
  "mcpServers": {
    "getweb": {
      "command": "npx",
      "args": [
        "mcp-getweb"
      ],
      "type": "stdio",
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
        "GOOGLE_SEARCH_ENGINE_ID": "YOUR_SEARCH_ENGINE_ID",
        "JINA_API_KEY": "YOUR_JINA_API_KEY"
      }
    }
  }
}
  1. Ensure you have Node.js installed on your machine (LTS version is recommended).
  2. Save the MCP server configuration shown above into a file named mcp-config.json in your project directory.
  3. Start the server with the configured environment variables set.
GOOGLE_API_KEY=YOUR_GOOGLE_API_KEY \
GOOGLE_SEARCH_ENGINE_ID=YOUR_SEARCH_ENGINE_ID \
JINA_API_KEY=YOUR_JINA_API_KEY \
npx mcp-getweb

Configuration and environment

The server is configured as a stdio MCP endpoint with a single MCP entry named getweb. It uses three environment variables to access external services. You pass these values at start time or within your process manager to keep credentials secure.

{
  "mcpServers": {
    "getweb": {
      "command": "npx",
      "args": ["mcp-getweb"],
      "type": "stdio",
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
        "GOOGLE_SEARCH_ENGINE_ID": "YOUR_SEARCH_ENGINE_ID",
        "JINA_API_KEY": "YOUR_JINA_API_KEY"
      }
    }
  }
}

Security and best practices

Keep API keys and keys to external services out of source control. Use your environment management or secret storage to inject GOOGLE_API_KEY, GOOGLE_SEARCH_ENGINE_ID, and JINA_API_KEY at runtime. Rotate keys periodically and monitor usage for unusual activity.

Troubleshooting and notes

If you encounter connection issues, verify that your environment variables are correctly set and that the MCP client you use can reach the running GetWeb instance. Check network access and permissions for any endpoints you rely on, especially when performing web fetches or Google-based searches.

Available tools

duckduckgo-search

Search the web using DuckDuckGo with HTML scraping and return results.

google-search

Query Google Programmable Search Engine and return relevant results with optional constraints like site, language, date, and sort.

felo-search

AI-powered search for up-to-date technical information, including releases, advisories, migrations, and community insights.

fetch-url

Fetch the clean content from a URL and return it as plain text.

url-metadata

Extract metadata from a URL, including title, description, image, and favicon.

url-fetch

Fetch a web page and convert it to Markdown, handling HTML, plaintext, and JSON.

jina-reader

Retrieve LLM-friendly content from a URL with optional summaries and format variants.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational