Fetch
Fetch a web page and return it as clean markdown for the agent, in chunks for long pages. The reference server from the Model Context Protocol project.
{ "mcpServers": { "modelcontextprotocol-server-fetch": { "command": "uvx", "args": [ "mcp-server-fetch" ] } }}.cursor/mcp.jsonMCP server
- Transport
- stdio
- Tools
- 1
- Status
- Local
Power your agent
Add this server
The publisher's own command. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
Local command
uvx mcp-server-fetchClaude Code has no install link for a local command. Copy the command below and run it in a terminal.
shClaude Code
claude mcp add modelcontextprotocol-server-fetch -- uvx mcp-server-fetchRun in a terminal.
jsonClaude Desktop
{ "mcpServers": { "modelcontextprotocol-server-fetch": { "command": "uvx", "args": [ "mcp-server-fetch" ] } }}claude_desktop_config.json
Local · pypiPublisher installStep-by-step: add this in Claude
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
Host a copy with our keys and logs.
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchServer facts
Local- Transport
- stdio
- Last checked
- 2026-11-05
- Stars
- 92k
- Tools
- 1
- Uptime
- —
Overview
About Fetch
The reference fetch server from the Model Context Protocol project. Give it a URL and it fetches the page and converts the HTML to markdown, so the agent reads the content without the markup. Long pages come back in chunks with a start index. It respects robots.txt unless you turn that off.
1 tool
Tools
tools/list
FAQ
Questions
How do I install Fetch?
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
Does Fetch need an API key?
No required environment variable is listed on this record.
What transport does Fetch use?
Fetch runs locally over stdio.
When was Fetch last checked?
Last checked 2026-11-05. Fetch a URL and read it as markdown.
From the publisher
Documentation
README is not crawled yet. Open the repository