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 — 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 | — | Custom headers |
body |
any | — | 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 |
|---|---|---|
| 🇩🇪 Frankfurt | eu-frankfurt |
Germany |
| 🇦🇺 Sydney | ap-sydney |
Australia |
| 🇺🇸 San Francisco | us-west |
California |
| 🇺🇸 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.
- 🌍 4 regions — fetch from where your users are
- ⚡ Sub-300ms — optimized proxy, not a browser farm
- 🔒 No IP leaking — your agent's identity stays hidden
- 📸 Screenshots + JS rendering — see what humans see
- 🤖 Built for agents — 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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。