Refetch MCP Server

by lowenbjer Your server? Claim it

answering

Refetch is answering right now. Last checked moments ago.

Fetch pages as markdown, search web and news, extract structured data. For AI agents.

Uptime history 47 days of history

47 days agonow

100.0%

Uptime 24h

92 of 92 checks

—

Tools

hidden behind auth

358 ms

Response time

average over 24h

authentication required

Access

streamable-http

Nothing serious here today

Today is the operative word: we check Refetch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add refetch --transport http https://refetch.cloud/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "refetch": {
      "url": "https://refetch.cloud/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.refetch]
url = "https://refetch.cloud/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "refetch": {
      "url": "https://refetch.cloud/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "refetch": {
      "url": "https://refetch.cloud/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.

Endpoints

URL	Transport	State	Latency	Checked
https://refetch.cloud/mcp	streamable-http	needs auth	430 ms	0 min ago

Alternatives to Refetch

same job, measured the same way

MCP Browser Research

by infoinlet-marketplace

Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.

30 installs/wk local only

Sofya

by sofya

Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.

4 tools answering

Vanshulgoyal101

by vanshulgoyal101

Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.

4 tools answering

срезAI — Search API for AI agents

by srezai

Web search, page reading and structured extraction for AI agents, with strong RU coverage

10 tools answering

Perpage MCP Server

by cal-dev-tech

Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.

39 installs/wk local only

by neurobird

Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.

2 tools answering

MCP Research Agent: Web Scraping Tool for AI

by ranovam

Structured web research tool for AI agents: search, fetch and shape web data into the JSON schema…

answering

FastAF

by fastaf

Web data tools for AI agents: pages as markdown, search, maps, commerce, jobs, AI answers.

answering

Refetch — questions

Answers built from our own checks of this server.

Why is there no tool list for Refetch?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is Refetch working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 358 ms. The bar chart above shows every period we have measured.

How do I connect Refetch?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own credentials: it refuses anonymous clients.

Does Refetch need an API key?

Yes. Every time we knock, Refetch answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Refetch?

It answers our handshake in 358 ms on average, which is faster than 43% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.