Fetch
zcaceres/fetch-mcp
Fetch MCP provides tools for retrieving and converting web content into multiple formats including HTML, plain text, Markdown, JSON, and readable article extracts. The server offers six primary tools—fetch_html, fetch_txt, fetch_markdown, fetch_json, fetch_readable (using Mozilla Readability), and fetch_youtube_transcript—each accepting common parameters like custom headers, character limits, start indices, and proxy configuration. It solves the problem of extracting and reformatting web content for AI applications by handling format conversion, content cleanup, and transcript retrieval across diverse source types.
- GitHub stars
- 758
- tools
- 6
- last updated
- Mar 4, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
fetch_htmlFetch a website and return its raw HTML content.
Fetch a website and return its raw HTML content.
No parameter schema in public metadata yet.
fetch_markdownFetch a website and return its content converted to Markdown.
Fetch a website and return its content converted to Markdown.
No parameter schema in public metadata yet.
fetch_txtFetch a website and return plain text with HTML tags, scripts, and styles removed.
Fetch a website and return plain text with HTML tags, scripts, and styles removed.
No parameter schema in public metadata yet.
fetch_jsonFetch a URL and return the JSON response.
Fetch a URL and return the JSON response.
No parameter schema in public metadata yet.
fetch_readableFetch a website and extract the main article content using Mozilla Readability, returned as Markdown.
Fetch a website and extract the main article content using Mozilla Readability, returned as Markdown.
No parameter schema in public metadata yet.
fetch_youtube_transcriptFetch a YouTube video's captions/transcript.
Fetch a YouTube video's captions/transcript.
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageReadme
Fetch MCP Server
fetch mcp logo
An MCP server for fetching web content in multiple formats — HTML, JSON, plain text, Markdown, readable article content, and YouTube transcripts.
Tools
All tools accept the following common parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | URL to fetch |
headers | object | No | Custom headers to include in the request |
max_length | number | No | Maximum characters to return (default: 5000) |
start_index | number | No | Start from this character index (default: 0) |
proxy | string | No | Proxy URL (e.g. http://proxy:8080) |
-
fetch_html — Fetch a website and return its raw HTML content.
-
fetch_markdown — Fetch a website and return its content converted to Markdown.
Details
- Repository
- github.com/zcaceres/fetch-mcp
- Category
- Search & Web Crawling
