WebFetch MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@WebFetch MCP Server Fetch https://example.com and summarize the main points."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WebFetch MCP Server
A Model Context Protocol (MCP) server that fetches web pages, converts HTML to markdown, and uses Claude to answer questions about the content. Get AI-powered summaries and analysis of any web page from any MCP client.
View on mpak registry | Built by NimbleBrain
Install
Install with mpak:
mpak install @nimblebraininc/webfetchConfiguration
Get your API key from Anthropic Console, then configure:
mpak config set @nimblebraininc/webfetch anthropic_api_key YOUR_API_KEYClaude Code
claude mcp add webfetch -- mpak run @nimblebraininc/webfetchClaude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"webfetch": {
"command": "mpak",
"args": ["run", "@nimblebraininc/webfetch"]
}
}
}See the mpak registry page for full install options.
Related MCP server: fetch
Tools
web_fetch
Fetch a web page and answer questions about its content. The page is fetched, converted to markdown, and sent to Claude Haiku for analysis.
Parameter | Type | Required | Description |
|
| Yes | URL to fetch. HTTP URLs are auto-upgraded to HTTPS. |
|
| Yes | Question or instruction about the page content. |
Example call:
{
"name": "web_fetch",
"arguments": {
"url": "https://example.com",
"prompt": "What is this page about? Summarize the main points."
}
}Example response:
This page is the IANA example domain, reserved for use in documentation
and examples. It contains a simple heading and a paragraph explaining
that the domain is established for illustrative purposes.Features:
Automatic HTTP to HTTPS upgrade
HTML cleaned and converted to markdown (strips scripts, styles, nav, headers, footers)
15-minute in-memory cache for repeated fetches of the same URL
Cross-host redirect detection (returns redirect URL for you to follow)
Content truncation for very large pages
Quick Start
Local Development
git clone https://github.com/NimbleBrainInc/mcp-webfetch.git
cd mcp-webfetch
# Install dependencies
uv sync
# Set API key
export ANTHROPIC_API_KEY=your-key-here
# Run the server (stdio mode)
uv run python -m mcp_webfetch.serverThe server supports HTTP transport with:
Health check:
GET /healthMCP endpoint:
POST /mcp
Development
# Install with dev dependencies
uv sync --group dev
# Run all checks (format, lint, typecheck, unit tests)
make check
# Run unit tests
make test
# Run with coverage
make test-covAbout
WebFetch MCP Server is published on the mpak registry and built by NimbleBrain. mpak is an open registry for Model Context Protocol servers.
License
MIT
Available Tools
1 toolweb_fetchWeb FetchB
Fetch a web page and answer questions about its content.
Fetches the URL, converts HTML to markdown, and uses Claude to answer the prompt based on the page content.
Inputs: url (required), prompt (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another tool in this server. Its purpose is clearly scoped to fetching a web page and answering questions about the content.
With a single tool, naming consistency is trivially satisfied. The name web_fetch is clear and follows a standard snake_case convention.
The server is narrowly focused on a single capability, so one tool is coherent with its purpose. However, one tool is thin relative to typical MCP servers and leaves little flexibility for different fetch-related workflows.
The core operation of fetching a page and answering a prompt about it is covered. Minor gaps exist around raw content retrieval, explicit extraction-only mode, or fetch configuration, but these are workarounds rather than critical omissions.
Maintenance
Related MCP Connectors
Fetch any URL and get clean Markdown. Web scraping for AI agents.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
Turn web pages into clean Markdown text for LLMs and RAG. Respects robots.txt.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables Claude and other LLMs to read and parse web content, with smart fallback strategies to bypass access restrictions (e.g., paywalls, Cloudflare) and output Markdown.548MIT
- AlicenseNot gradedqualityDmaintenanceFetches web pages and converts them to markdown for LLM consumption, supporting chunked reading and raw content extraction.MIT
- FlicenseNot gradedqualityDmaintenanceFetches web content, converts HTML to Markdown, and processes it with Claude AI, bypassing common bot blocks.-
- FlicenseNot gradedqualityDmaintenanceFetches webpages and returns clean, structured Markdown with metadata (title, author, publish date, description, domain, word count).1-