Fetchvf.sr

listing.by · home.legend.verified

Fetch web pages by URL and convert the HTML to markdown, with chunked reading for long pages.

state.local.long (state.local.title)listing.badge.runs_with

listing.install

listing.local.explain

uvx mcp-server-fetch

listing.local.needs listing.local.note

act.add_to a11y.new_tabact.add_to a11y.new_tab

listing.share.h

listing.share.p_local

mcp.tc/i/fetch

listing.about

Fetch is a reference MCP server that retrieves a web page from a URL and returns its content as markdown, or as raw content if requested. Responses are truncated, and a start index lets the model read long pages in chunks until it finds what it needs.

It runs locally over stdio, started with uvx, pip or Docker. No API key is needed. By default it obeys robots.txt for model-initiated requests, and it supports custom user agent and proxy arguments. The README warns that it can reach local and internal IP addresses, so use it with care. Installing Node.js is optional and switches to a different HTML simplifier.

listing.can

  • Fetch a URL and extract its contents as markdown
  • Return raw page content without conversion
  • Read long pages in chunks with a start index
  • Limit the number of characters returned
  • Respect robots.txt, with an option to ignore it
  • Set a custom user agent or proxy

listing.tools

listing.notools.local

listing.prompts

  • Fetch https://example.com/blog/post and summarize it

  • Read the docs page at this URL and list the setup steps

  • Get the raw HTML of https://example.com

  • Continue reading that page from character 5000

listing.setup.h

listing.setup.local

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio fetch -- uvx mcp-server-fetch
  1. Start Claude Code and type /mcp. fetch should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Add to Cursor a11y.new_tab

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Needs uv (Python) on your computer.

VS Code

Install in VS Code a11y.new_tab

Or from a terminal:

code --add-mcp '{"name":"fetch","type":"stdio","command":"uvx","args":["mcp-server-fetch"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "fetch": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add fetch -- uvx mcp-server-fetch

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.fetch]
command = "uvx"
args = ["mcp-server-fetch"]

Needs uv (Python) on your computer.

Gemini CLI

gemini mcp add fetch uvx mcp-server-fetch

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer.

listing.faq

Can I paste mcp.tc/i/fetch into my MCP client?

No. Fetch runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx mcp-server-fetch.

Does Fetch need an API key?

No. It doesn't declare any keys or environment variables. It runs with your user account's permissions, so check what its tools can reach.

Is Fetch a remote or a local server?

Local. Your client starts it as a process on your computer with uvx mcp-server-fetch, which needs uv (Python).

What can Fetch do?

You can Fetch a URL and extract its contents as markdown, return raw page content without conversion and read long pages in chunks with a start index.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc's robot read Fetch's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead_local listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![Fetch on mcp.tc](https://mcp.tc/i/fetch/badge.svg)](https://mcp.tc/i/fetch)
HTML
<a href="https://mcp.tc/i/fetch"><img src="https://mcp.tc/i/fetch/badge.svg" alt="Fetch on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/fetch.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/fetch" title="Fetch on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json_local

https://mcp.tc/i/fetch.json

listing.em.fields

listing.related

listing.more_in

  • Gitvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Read, search and manipulate local Git repositories from your AI assistant.

    mcp.tc/i/git

  • Filesystemvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Read, write, search and edit files inside directories you explicitly allow, over a local stdio connection.

    mcp.tc/i/filesystem

  • Memoryvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Store and recall persistent memory across sessions using a local knowledge graph.

    mcp.tc/i/memory

  • Sequential Thinkingvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Work through problems as a sequence of thoughts that can be revised, branched and extended as understanding grows.

    mcp.tc/i/sequential-thinking

  • Timevf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Get the current time in any IANA timezone and convert times between timezones.

    mcp.tc/i/time

  • Brave Search

    Brave

    state.local.label (state.local.title)

    Search the web, news, images, videos and places using Brave's independent search index and get AI summaries.

    mcp.tc/i/brave-search

listing.disclaimer_checked