What is MCP Fetch Server?
The official MCP Fetch Server lets AI clients retrieve the content of any public URL and receive it as clean Markdown, plain text, or raw HTML. It handles redirects, follows canonical links, and strips navigation and boilerplate from most article pages.
Read the full overview
It is the simplest way to give Claude the ability to read a documentation page, a blog post, or a GitHub issue without copy-pasting the content into the chat window. No API key is required.
Fetch web pages and convert them to clean Markdown for Claude
Key capabilities
URL fetching
Retrieve any public URL and receive its main content as Markdown. The server uses readable-content extraction to remove navigation, ads, and footer clutter from most web pages before returning the result.
Raw mode
Optionally receive the full raw HTML for pages where the extraction heuristic strips too much, such as documentation pages with rich code blocks or structured tables.
Where MCP Fetch Server fits
Compatible with Claude Desktop, Cursor, Cline, and any MCP-compatible client. Install via npm (npx) or pip (uvx) depending on the server implementation language.
Positioning and limitations
A zero-configuration complement to the Brave Search server: use Brave to find relevant URLs, then use Fetch to read the full content of each page. Together they cover most research and documentation workflows without leaving the AI client.
MCP servers extend AI clients beyond their training data by giving them access to live systems: local files, databases, APIs, and services. Each server adds a set of typed tools the AI can call, inspect results from, and chain into multi-step workflows, all within a single conversation context.
“Fetch web pages and convert them to clean Markdown for Claude”
Technical details
- Access
- See vendor
- Source model
- Open source
- License
- Verify license
- Founded
- Not specified
- Pricing model
- Free
- API
- Not specified
- Website
- github.com ↗
- GitHub
- Source repository ↗
What to verify
Start from the users, systems and operating responsibilities the tool needs to support.
- Confirm current features, licensing and support terms.
- Validate deployment, data location and access control.
- Test integrations, exports and recovery workflows.
Install
npx -y @modelcontextprotocol/server-fetchReviews of MCP Fetch Server
No published reviews yet.
Loading review form…