web-retrieval-mcp

io.github.VelvetSP/web-retrieval-mcp

MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.

View repository →Homepage →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "web-retrieval-mcp": {
      "command": "uvx",
      "args": [
        "web-retrieval-mcp"
      ],
      "env": {
        "EXA_API_KEY": "<your EXA_API_KEY>",
        "FIRECRAWL_API_KEY": "<your FIRECRAWL_API_KEY>"
      }
    }
  }
}
Environment variables
  • EXA_API_KEYrequiredsecretExa API key (free tier at https://exa.ai)
  • FIRECRAWL_API_KEYrequiredsecretFirecrawl API key (free tier at https://firecrawl.dev)

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
0.1.2
Registry
active
Published
6/2/2026

More Search & Web servers

Browse all Search & Web →

CrawlEyes MCP Server

waiky-github

Web scraping & search for AI agents: extract, SearXNG search, rerank, robots compliance. No API key.

Search & WebAdded 2 months ago

Wick

wickproject

Browser-grade web access for AI agents. Fetches any webpage, returns clean markdown.

Search & WebAdded 7 months ago

io.github.x-hannibal/webshift

x-hannibal

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

Search & WebAdded 6 months ago

io.github.x-monk/webshift

x-monk

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

Search & WebAdded 7 months ago

io.github.Xavierfok/singapore-proxy-mcp

Xavierfok

Browse the web and run Google search through real Singapore mobile carrier IPs.

Search & WebAdded 1 month ago

Crawlberg

xberg-io

Scrape, crawl, and map websites to Markdown or JSON via local CLI.

Search & WebAdded 2 weeks ago

Add the badge to your site

Show visitors that web-retrieval-mcp is listed here — it’s also the link we check for a free listing.

web-retrieval-mcp — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-velvetsp-web-retrieval-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="web-retrieval-mcp — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![web-retrieval-mcp — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-velvetsp-web-retrieval-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.