Markdown fetch
Fetch a URL and convert HTML to Markdown.
Documentation ↗MCP server / web & research / source-linked
Fetch MCP Server
URL-fetching reference server that converts web pages to model-readable text. Use this record to separate documented interface facts from proposed evaluation steps, and preserve the checked date with the source links when the provider changes its setup.
Before you choose.
Identify the implementation and the job it supports.
Which implementation is this?
URL-fetching reference server that converts web pages to model-readable text. Use this record to separate documented interface facts from proposed evaluation steps, and preserve the checked date with the source links when the provider changes its setup.
Implementation source ↗
URL-fetching reference server that converts web pages to model-readable text. Use this record to separate documented interface facts from proposed evaluation steps, and preserve the checked date with the source links when the provider changes its setup.
Implementation source ↗
URL-fetching reference server that converts web pages to model-readable text. Use this record to separate documented interface facts from proposed evaluation steps, and preserve the checked date with the source links when the provider changes its setup.
Setup and connection.
The documented interface, authentication and installation path.
- Connection / transport
- stdio
- Authentication
- No provider key for public URLs; outbound HTTP.
Use uvx mcp-server-fetch with a known URL; continue long pages with start_index.
Setup reference ↗Documented setup example. Review the source and credentials before running; this command was not executed for this article.
uvx mcp-server-fetchWhat it actually exposes.
Concrete capabilities with maintainer sources.
Chunking
Continue beyond truncation using start_index.
Documentation ↗Raw mode
Request raw content when conversion loses needed context.
Documentation ↗Evidence and method.
What was checked and what was not tested.
HOW
Source method
Public maintainer documentation and repositories. This is not a hands-on product review.
WHEN
Last checked 2026-10-01
Setup examples are documented examples. Suggested trials and comparison advice are editorial guidance.
Sources support the adjacent factual statements. A source review does not establish uptime, performance, security or current account eligibility. Read the editorial policy.
Try a specific task.
A bounded evaluation you can reproduce in your own environment.
Extract an installation prerequisite (proposed; not tested)
Suggested evaluation, not an observed test result.
- Supply a known public docs URL.
- Fetch the relevant section and continue if truncated.
- Cite the page and label missing facts unknown.
What to inspect: Source-linked answer; proposed, not run.
Workflow reference ↗Permissions and limitations.
Read these constraints before granting access.
It can reach local or internal IP addresses; review SSRF risk.
Boundary reference ↗Editorial inference: fetching a page does not prove authenticated or interactive workflow completion.
Boundary reference ↗Decide by workflow.
Make the expected output explicit before you connect.
Source-linked answer; proposed, not run.
Keep the task inputs, tool calls, output and any errors together when you evaluate. The trial above is a proposal, not a recorded result.
Compare the alternatives.
Specific reasons to choose another route, with the tradeoff shown.
| Alternative | Choose it when | Tradeoff |
|---|---|---|
| Tavily MCP | Editorial inference: you need discovery before retrieval. | Adds provider service limits. Documentation ↗ |
| Playwright MCP | Editorial inference: you need clicks or authenticated browser state. | Adds browser runtime complexity. Documentation ↗ |
Questions before setup.
Answers specific to this implementation.
Is it a search engine?
No; the tool takes a URL.
Documentation ↗
Why incomplete?
Responses can truncate; continue with start_index.
Documentation ↗
Source trail.
Maintainer documentation used in this record.