A Model Context Protocol (MCP) server that provides web search, Wikipedia search, and web content fetching capabilities, written in OCaml using the
Snf MCP becomes available to MCP clients through the snf mcp mcp server. A Model Context Protocol (MCP) server that provides web search, Wikipedia search, and web content fetching capabilities, written in OCaml using the eio asynchronous runtime.
A Model Context Protocol (MCP) server that provides web search, Wikipedia search, and web content fetching capabilities, written in OCaml using the eio asynchronous runtime.
Once connected, the assistant can call these 5 tools directly:
search — The search tool exposed by this serversearch_wikipedia — The search_wikipedia tool exposed by this serverfetch_content — The fetch_content tool exposed by this serverfetch_markdown — The fetch_markdown tool exposed by this serverLMStudio — Edit the json file from the interface adding the same json entry as in the LLM CLI example above. See also the [officialThe server is distributed via PyPI as trafilatura, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Search and scraping servers exist to fix the single most common failure of any assistant: answering from stale training data instead of what is on the web today. Snf MCP sits in that group, and the shape of its toolset — search, search_wikipedia, fetch_content among others — tells you what it is really for. Worth comparing against the other search web scraping servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| search | The search tool exposed by this server. |
| search_wikipedia | The search_wikipedia tool exposed by this server. |
| fetch_content | The fetch_content tool exposed by this server. |
| fetch_markdown | The fetch_markdown tool exposed by this server. |
| LMStudio | Edit the json file from the interface adding the same json entry as in the LLM CLI example above. See also the [official documentation](https://lmstudio.ai/docs/app/plugins/mcp). |
{
"mcpServers": {
"snf": {
"command": "uvx",
"args": ["trafilatura"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.