Free and open source, from the makers of AliasMode.
anyfetch is an MCP project maintained in the aliasmode/anyfetch repository. The maintainer describes its purpose as “Free and open source, from the makers of AliasMode”. Read the project documentation for the complete scope.
The documented npm package is @aliasmode/anyfetch. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-13.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| url | The page to read. |
| query | The search query. Quoted phrases work. |
| max_chars | Optional. The most content characters per page. By default the pages share 50,000. |
| offset | Optional. The first content character to return. Not used with a query. |
| fresh | Optional. As for web_fetch. |
| urls | The pages to read. They are fetched at the same time. |
| provider | Optional. See the list below. The default is auto. |
| site | Optional. Keep results from one domain, for example docs.rs. |
| time | Optional. day, week, month or year. |
| page | Optional. The result page, from 1. |
| read | Optional. Also return, from this many top results, the parts of each page that match the query. |
| searxng_url | The base URL of your SearXNG instance, for the searxng provider. It must have JSON output on. |
| Provider | Source |
| auto | Brave, then Yahoo, then DuckDuckGo: each one when the one before gives no results. |
| brave | Brave Search. About 20 results per page. |
| yahoo | Yahoo Search. 7 results per page. No year filter. |
| duckduckgo | DuckDuckGo. First page only. |
| searxng | Your own SearXNG instance. |
| github | GitHub repositories, with stars and language. |
| stackoverflow | Stack Overflow questions, with score and answer count. |
| hackernews | Hacker News stories, with points and the discussion link. |
| arxiv | arXiv papers, with abstracts. |
| papers | Research papers from OpenAlex, with citation counts and open-access links. |
| Code | Meaning |
| challenge_required | The site answered with a bot challenge that needs a browser. |
| http_error | The site refused the request. status has the HTTP code. |
| rate_limited | The site asked to slow down. retry_after has the wait, when given. |
| timeout | The site did not answer within 30 seconds. |
| unsupported_content | The URL is not text or a PDF (an image, for example). |
| extraction_failed | The page has no readable content. A scanned PDF has no text. |
| web_fetch | |
| web_fetch_many | |
| web_search |
{
"mcpServers": {
"anyfetch": {
"command": "npx",
"args": [
"-y",
"@aliasmode/anyfetch",
"mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.