Skip to content
anavem.com
Newsletter

MCP server

Fetch MCP Server

Reference MCP server from the Model Context Protocol organization. It lets an MCP client retrieve a web page by URL and convert the HTML to markdown for the language model.

Maintainer
Model Context Protocol organization (reference server in the modelcontextprotocol/servers repository)
Licence
Repository LICENSE: MIT to Apache-2.0 transition (see limitations)
Last release
2026.8.31, released 2026-08-31 (repository-wide release shown on the modelcontextprotocol/servers releases page; the src/fetch pyproject.toml shows version 0.6.3)
Last verified Jump to what it can access ↓

What it can access

An MCP server gives an AI application a set of capabilities, and it can do only what its code and the credentials you give it allow. This is what the listing states, based on the sources below. Anavem does not rate it safe or unsafe: check it against what you plan to use it for.

Permissions it asks for

  • One tool (per README): fetch, with parameters url (required), max_length (default: 5000), start_index (default: 0) and raw (default: false); the README also lists a fetch prompt
  • Makes outbound HTTP requests to the URLs the model asks for
  • README states the server can access local/internal IP addresses

Data it can reach

Retrieves content from any URL the client passes to it, including local or internal addresses per the README security notice. The README does not name the transport; its configurations start the server as a command (uvx, docker or python), and per the MCP architecture page (2026-10-03) a server using the STDIO transport is a local process on the same machine as the client. The README states robots.txt is obeyed by default if the request came from the model (not if user-initiated) and can be disabled with --ignore-robots-txt. Fetched page content is returned to the AI application.

How it is installed or connected

Steps copied from the official README (https://github.com/modelcontextprotocol/servers/tree/main/src/fetch, read 2026-10-03):

  1. uv (the README heading is "Using uv (recommended)"): no specific installation is needed; the README runs uvx directly, as in the configuration below (command uvx, args ["mcp-server-fetch"])
  2. pip: pip install mcp-server-fetch, then python -m mcp_server_fetch
  3. Docker, as a configuration: command docker, args ["run", "-i", "--rm", "mcp/fetch"]
  4. Claude.app configuration (uvx), as shown in the README:
{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Optional arguments listed in the README: --ignore-robots-txt, --user-agent=YourUserAgent, --proxy-url.

Limitations

  • Licence detail: Repository LICENSE: the project is "undergoing a licensing transition from the MIT License to the Apache License, Version 2.0"; new code is Apache-2.0 and contributions without relicensing consent remain MIT. The src/fetch pyproject.toml states MIT and the src/fetch README License section states MIT.
  • README security notice: "This server can access local/internal IP addresses and may represent a security risk."
  • The repository README describes the servers as reference implementations meant as educational examples, not production-ready solutions.
  • The README says the tool extracts page content as markdown and truncates the response (default max_length 5000, with start_index to read in chunks); it does not describe any filtering of page content for malicious or untrusted text.
  • Anavem has not audited this software.

Not sure what to look for? Read what to check before installing.

Quick answers

Who maintains this MCP server?
Model Context Protocol organization (reference server in the modelcontextprotocol/servers repository).
What can it access?
It asks for: One tool (per README): fetch, with parameters url (required), max_length (default: 5000), start_index (default: 0) and raw (default: false); the README also lists a fetch prompt, Makes outbound HTTP requests to the URLs the model asks for, README states the server can access local/internal IP addresses. Retrieves content from any URL the client passes to it, including local or internal addresses per the README security notice. The README does not name the transport; its configurations start the server as a command (uvx, docker or python), and per the MCP architecture page (2026-10-03) a server using the STDIO transport is a local process on the same machine as the client. The README states robots.txt is obeyed by default if the request came from the model (not if user-initiated) and can be disabled with --ignore-robots-txt. Fetched page content is returned to the AI application. We do not label anything safe or unsafe; read the official sources before you install.
What licence does it use?
Repository LICENSE: MIT to Apache-2.0 transition (see limitations). Check the terms if you plan to use it commercially.
What are its limitations?
Licence detail: Repository LICENSE: the project is "undergoing a licensing transition from the MIT License to the Apache License, Version 2.0"; new code is Apache-2.0 and contributions without relicensing consent remain MIT. The src/fetch pyproject.toml states MIT and the src/fetch README License section states MIT. README security notice: "This server can access local/internal IP addresses and may represent a security risk.". The repository README describes the servers as reference implementations meant as educational examples, not production-ready solutions. The README says the tool extracts page content as markdown and truncates the response (default max_length 5000, with start_index to read in chunks); it does not describe any filtering of page content for malicious or untrusted text. Anavem has not audited this software.
When was it last released?
2026.8.31, released 2026-08-31 (repository-wide release shown on the modelcontextprotocol/servers releases page; the src/fetch pyproject.toml shows version 0.6.3). Verified Oct 3, 2026.

Sources

Related listings

Other listings in the same category.

All MCP servers →
MCP server

Sentry MCP Server

MCP server published by Sentry that connects AI assistants to Sentry to search errors, analyze performance, triage issues, read documentation and manage projects, as a hosted remote service or a local stdio process.

By Sentry (getsentry organization on GitHub; hosted at mcp.sentry.dev) · Verified Oct 3, 2026

MCP server

Exa MCP Server

MCP server published by Exa Labs. It connects an MCP client to Exa for web search, fetching clean content from known URLs, and multi-step research, through a hosted remote endpoint; Exa docs also describe a local npm package.

By Exa Labs (exa-labs organization on GitHub; documented on exa.ai) · Verified Oct 3, 2026

MCP server

Brave Search MCP Server

MCP server published by Brave Software that connects an MCP client to the Brave Search API for web, local, video, image, news and place search, plus AI-oriented context retrieval and summaries.

By Brave Software (github.com/brave organization; linked from Brave's Search API tools page) · Verified Oct 3, 2026