Fetch MCP Server
This server wraps HTTP fetching with built-in guardrails and content transformation. It handles SSRF protection out of the box, so you don't have to worry about accidentally hitting internal endpoints. Beyond basic fetching, it converts HTML to markdown, extracts reader mode content for cleaner article text, and pulls metadata from pages. Reach for this when you need Claude to safely grab and parse web content without building your own sanitization layer. It's essentially a hardened fetch with intelligent content extraction baked in.
- GitHub stars
- 2
- tools
- 15
- transport
- STDIO
- last updated
- Nov 12, 2026
Tools
15 toolsPublic tool metadata for what this MCP can expose to an agent.
http_getPerforms an HTTP GET request to an absolute URL.
Performs an HTTP GET request to an absolute URL.
No parameter schema in public metadata yet.
http_postPerforms an HTTP POST request with optional body.
Performs an HTTP POST request with optional body.
No parameter schema in public metadata yet.
http_putPerforms an HTTP PUT request with optional body.
Performs an HTTP PUT request with optional body.
No parameter schema in public metadata yet.
http_patchPerforms an HTTP PATCH request with optional body.
Performs an HTTP PATCH request with optional body.
No parameter schema in public metadata yet.
http_deletePerforms an HTTP DELETE request with optional body.
Performs an HTTP DELETE request with optional body.
No parameter schema in public metadata yet.
http_headPerforms an HTTP HEAD request.
Performs an HTTP HEAD request.
No parameter schema in public metadata yet.
http_optionsPerforms an HTTP OPTIONS request.
Performs an HTTP OPTIONS request.
No parameter schema in public metadata yet.
fetch_html_to_markdownFetches a URL and converts the HTML to markdown with scripts, styles and navigation stripped.
Fetches a URL and converts the HTML to markdown with scripts, styles and navigation stripped.
No parameter schema in public metadata yet.
fetch_html_to_textFetches a URL and returns plain text with block-level structure preserved as newlines.
Fetches a URL and returns plain text with block-level structure preserved as newlines.
No parameter schema in public metadata yet.
fetch_readerIsolates the main article body of a page and returns it as markdown with title, byline and word count.
Isolates the main article body of a page and returns it as markdown with title, byline and word count.
No parameter schema in public metadata yet.
fetch_metaFetches a URL and returns its head metadata (title, description, Open Graph, Twitter, JSON-LD, icons, feeds) without downloading the full body.
Fetches a URL and returns its head metadata (title, description, Open Graph, Twitter, JSON-LD, icons, feeds) without downloading the full body.
No parameter schema in public metadata yet.
fetch_linksFetches a page and returns every anchor href resolved to an absolute URL, classified as internal or external.
Fetches a page and returns every anchor href resolved to an absolute URL, classified as internal or external.
No parameter schema in public metadata yet.
fetch_sitemapFetches a sitemap.xml or sitemap index and returns the URL list.
Fetches a sitemap.xml or sitemap index and returns the URL list.
No parameter schema in public metadata yet.
fetch_feedParses an RSS 2.0 or Atom 1.0 feed and returns its entries.
Parses an RSS 2.0 or Atom 1.0 feed and returns its entries.
No parameter schema in public metadata yet.
fetch_robotsFetches and parses robots.txt and reports whether a path is allowed for a user agent.
Fetches and parses robots.txt and reports whether a path is allowed for a user agent.
No parameter schema in public metadata yet.
Sponsors
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 languageReadme
@yawlabs/fetch-mcp
One click adds this to your local Yaw MCP config so it's available in every Yaw Terminal session. Or install manually below.
A comprehensive HTTP fetch MCP server for AI assistants. Bring-your-own client: runs as a stdio MCP server so any MCP-compatible client (Claude Code, Claude Desktop, Cursor, mcph, …) can fetch web content safely.
What it gives the model
Details
- Repository
- github.com/yawlabs/fetch-mcp
- Website
- yaw.sh/mcp-servers/fetch-mcp
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
@yawlabs/fetch-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from yawlabs
Related Documents & Knowledge MCP servers
View all
Pharaohpharaoh-so/pharaoh-mcpCodebase knowledge graph — architectural awareness for AI coding agents via MCP2stars
Knowmintsou0327/knowmintAI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.2stars
Mnemographtm42/mnemographEvent-sourced knowledge graph memory for AI coding agents with semantic search2stars
AgentBasevhspace/agentbaseShared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.2stars
AI-First Scraperyubinkim444/ai-first-scraper-mcpThree MCP tools: fetch_page, fetch_pages_batch, search_web. Ad-free Markdown for AI agents.2stars
Agent Moduleagentmodule/mcpDeterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.0stars