MCProxy
An MCP server that gives AI agents on-demand access to proxies from the world's leading and Russian/CIS proxy providers — through a single, unified interface.
README
MCProxy
An MCP server that gives AI agents on-demand access to proxies from the world's leading and Russian/CIS proxy providers — through a single, unified interface.
Built with FastMCP 3. When an agent needs a proxy, it calls one MCProxy tool; MCProxy talks to whichever provider you've configured and returns ready-to-use proxy strings.
Why
Every proxy provider has its own API, auth scheme, and quirks. MCProxy normalizes them behind one provider-agnostic tool surface so an agent (or you) can:
- discover which providers are configured and what they support,
- generate or list proxies with geo-targeting and rotation,
- buy and extend proxies where the provider's API allows it,
- check balance / usage and list targetable countries,
- run requests through managed scraping APIs,
…without learning each vendor's API.
How it works
AI agent ──MCP──> MCProxy (FastMCP server)
│
├─ unified tools: list_providers, get_proxies,
│ generate_proxy_list, buy_proxies, check_balance, …
│
└─ provider registry ─> per-provider adapters ─HTTP─> vendor APIs
Each provider is a small adapter that maps the vendor's API onto shared models
(ProxyEndpoint, BalanceInfo, CountryListResult, …). A registry exposes them,
and a handful of generic tools dispatch to the right adapter based on a provider
argument. This keeps the tool count low (great for token usage) while supporting
many providers.
Supported providers
Implemented adapters
| Provider | Region | Types | Operations |
|---|---|---|---|
| Webshare | 🌍 US | datacenter, ISP, residential | list, balance, usage, countries |
| IPRoyal | 🌍 LT | residential | generate, balance, usage, countries |
| ProxyMesh | 🌍 US | datacenter, ISP | list, countries, usage |
| ScraperAPI | 🌍 US | scraping API | scrape, usage |
| ScrapingBee | 🌍 FR | scraping API | scrape, usage |
| Proxy6 | 🇷🇺 RU | datacenter (IPv4/IPv6) | list, balance, countries, buy, extend |
| ProxyLine | 🇷🇺 RU | datacenter (IPv4/IPv6) | list, balance, countries, buy, extend |
| Proxy-Store | 🇷🇺 RU | datacenter, residential, mobile | list, balance, countries, buy, extend |
| Proxy-Seller | 🇷🇺 RU | IPv4/IPv6/ISP/mobile/residential | list, balance, countries |
| ASOCKS | 🇷🇺 RU/CIS | residential, mobile | balance |
| FineProxy | 🇷🇺 RU | datacenter, ISP, residential | balance |
Documented & planned
list_providers also surfaces a catalog of major providers with public APIs whose
adapters are planned: Bright Data, Oxylabs, Decodo (Smartproxy), SOAX, NetNut,
Infatica, Proxy-Cheap, Zyte, Nimble, Rayobyte (global) and Mobile Proxy Space,
iProxy.online, ProxyMarket, Froxy (RU/CIS). See
docs/PROVIDERS.md for the full landscape, API notes and sources.
Install
Requires Python 3.12+. uv recommended.
git clone https://github.com/evgenygurin/mcproxy.git
cd mcproxy
uv venv --python 3.12
uv pip install -e . # add ".[dev]" for tests/linting
Configure
Credentials are read from environment variables (or a local .env). Configure only
the providers you use. Copy .env.example and fill in your keys:
cp .env.example .env
# e.g.
WEBSHARE_API_KEY=...
IPROYAL_API_TOKEN=...
PROXY6_API_KEY=...
list_providers shows which providers are configured and the exact env var names
each one needs.
Run
# stdio (default — for Claude Desktop, Cursor, etc.)
uv run mcproxy
# or
uv run fastmcp run server.py:mcp
# HTTP transport
MCPROXY_TRANSPORT=http MCPROXY_PORT=8000 uv run mcproxy
Use with an MCP client
{
"mcpServers": {
"mcproxy": {
"command": "uv",
"args": ["run", "mcproxy"],
"env": {
"WEBSHARE_API_KEY": "your-key",
"PROXY6_API_KEY": "your-key"
}
}
}
}
Tools
| Tool | Purpose |
|---|---|
list_providers |
Discover providers, capabilities and config status. Start here. |
get_provider_info |
Capabilities for one provider. |
get_proxies |
List proxies already on your account (fixed-IP providers). |
generate_proxy_list |
Generate proxy strings with geo + rotation (residential pools). |
buy_proxies |
Purchase new proxies (spends money; supported providers only). |
extend_proxies |
Renew existing proxies by ID. |
check_balance / get_usage |
Monitor spend and traffic. |
list_countries |
Targetable locations for a provider. |
scrape |
Fetch a URL through a managed scraping API. |
acquire_proxy |
"Just give me a proxy" — picks a configured provider automatically. |
Every returned proxy includes a ready-to-use url (e.g. http://user:pass@host:port).
Settings
Global options use the MCPROXY_ prefix:
| Variable | Default | Description |
|---|---|---|
MCPROXY_TRANSPORT |
stdio |
stdio, http, or sse. |
MCPROXY_HOST / MCPROXY_PORT |
127.0.0.1 / 8000 |
HTTP bind address. |
MCPROXY_REQUEST_TIMEOUT |
30 |
Outbound HTTP timeout (seconds). |
MCPROXY_DEFAULT_PROVIDER |
– | Preferred provider for acquire_proxy. |
Development
uv pip install -e ".[dev]"
uv run pytest # tests (in-memory MCP client + mocked HTTP)
uv run ruff check . # lint
uv run mypy src # types
Adding a provider: create src/mcproxy/providers/<name>.py subclassing
BaseProvider, override the operations it supports, and register it in
src/mcproxy/providers/__init__.py. See webshare.py for a clean reference.
Disclaimer
Use proxies lawfully and in accordance with each provider's terms of service and applicable law. This project is an integration layer; it does not endorse misuse.
License
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。