klawfetch
A geo-distributed HTTP proxy for AI agents, enabling web fetching from multiple global regions (Frankfurt, Sydney, New York, San Francisco) with support for screenshots, scraping, and JS rendering.
README
@klawfetch/mcp-server
Your agent can't see the web from Tokyo. Now it can.
KlawFetch is a geo-distributed HTTP proxy built for AI agents. Fetch web content from Frankfurt, Sydney, New York, or San Francisco β with one API call.
This MCP server gives any Claude, OpenAI, or MCP-compatible agent instant access to KlawFetch's full capabilities.
Quick Start
# Install and run (needs Node.js 18+)
npx @klawfetch/mcp-server
Set your API key:
KLAWFETCH_API_KEY=your_key npx @klawfetch/mcp-server
Get an API key at klawkeeper.xyz
Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"klawfetch": {
"command": "npx",
"args": ["@klawfetch/mcp-server"],
"env": {
"KLAWFETCH_API_KEY": "your_key_here"
}
}
}
}
Restart Claude Desktop. Your agent now has geo-distributed web access.
Add to OpenAI / Other MCP Clients
Any MCP-compatible client works:
{
"mcpServers": {
"klawfetch": {
"command": "npx",
"args": ["@klawfetch/mcp-server"],
"env": {
"KLAWFETCH_API_KEY": "your_key_here"
}
}
}
}
Tools
fetch_url
Fetch any URL from a specific global region.
"Fetch https://example.com from Frankfurt"
"GET the homepage of news.ycombinator.com from Sydney"
"POST to https://api.example.com/data with body {key: value}"
Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
url |
string | (required) | URL to fetch |
method |
string | GET |
HTTP method |
headers |
object | β | Custom headers |
body |
any | β | Request body |
region |
string | auto | eu-frankfurt, ap-sydney, us-west, us-east |
follow_redirects |
boolean | true |
Follow redirects |
timeout |
number | 30000 |
Timeout in ms |
parse_json |
boolean | false |
Parse response as JSON |
screenshot
Capture a visual screenshot of any web page.
"Screenshot https://example.com at 1920x1080"
"Take a full-page screenshot of the dashboard"
scrape
Extract structured data using CSS selectors.
"Scrape all h2 titles and .price elements from https://shop.example.com"
render
Fetch with full JavaScript rendering (for SPAs/dynamic content).
"Render https://spa-app.com and wait for network idle"
list_regions
Check which regions are online.
"What KlawFetch regions are available?"
Direct API Usage (no MCP)
curl
# Fetch a URL from Frankfurt
curl -X POST https://klawfetch.xyz/v1/fetch \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com", "region": "eu-frankfurt"}'
Python
import requests
response = requests.post(
"https://klawfetch.xyz/v1/fetch",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={"url": "https://example.com", "region": "eu-frankfurt"}
)
data = response.json()
print(f"Status: {data['status']}, Body: {data['body'][:200]}")
TypeScript / Node.js
const res = await fetch("https://klawfetch.xyz/v1/fetch", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json",
},
body: JSON.stringify({
url: "https://example.com",
region: "eu-frankfurt",
}),
});
const data = await res.json();
console.log(`Status: ${data.status}, Body: ${data.body.slice(0, 200)}`);
Available Regions
| Region | ID | Location |
|---|---|---|
| π©πͺ Frankfurt | eu-frankfurt |
Germany |
| π¦πΊ Sydney | ap-sydney |
Australia |
| πΊπΈ San Francisco | us-west |
California |
| πΊπΈ New York | us-east |
New York |
Check real-time status: GET https://klawfetch.xyz/v1/regions
Pricing
| Operation | Credits |
|---|---|
| Fetch | 2 credits |
| Screenshot | 10 credits |
| Scrape | 5 credits |
| JS Render | 15 credits |
~1,000 simple fetches for $1. All regions included.
Free tier: 100 requests/day, no credit card required.
Get credits at klawkeeper.xyz. Pay with USDC, BTC, or card.
Why KlawFetch?
The problem: Your AI agent runs in us-east-1. Every web request comes from the same IP block. Sites geo-restrict content, rate-limit your region, or serve different data based on location.
The solution: KlawFetch routes requests through VPS nodes in 4 global regions. Your agent sees the web the way a human in Frankfurt, Sydney, or San Francisco would.
- π 4 regions β fetch from where your users are
- β‘ Sub-300ms β optimized proxy, not a browser farm
- π No IP leaking β your agent's identity stays hidden
- πΈ Screenshots + JS rendering β see what humans see
- π€ Built for agents β MCP-native, API-first, pay-per-request
Environment Variables
| Variable | Description |
|---|---|
KLAWFETCH_API_KEY |
Your KlawKeeper API key (required) |
KLAWFETCH_API_BASE |
Custom API base URL (default: https://klawfetch.xyz) |
License
MIT
Links
- API Docs: klawfetch.xyz
- Get API Key: klawkeeper.xyz
- Full Stack: klawstack.xyz
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.