Skip to main content
Glama
deenesjakoruzh
Iploop

ProxyClaw MCP Server

by Iploop
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

🌐 ProxyClaw MCPサーバー

IPLoopによるProxyClaw用Model Context Protocol (MCP) サーバー。

195カ国以上の1億7500万以上の住宅用IPを経由してWebリクエストをルーティングします。Claude Desktop、Cursor、Zed、またはMCP互換クライアントから直接利用可能です。

MCPサーバーを備えた唯一の住宅用プロキシネットワークです。 AIがデータセンターではなく、実際の家庭からブラウジングできるようになります。

✨ 特徴

  • 195カ国以上 — 実際の住宅用IPを経由してリクエストをルーティング

  • アンチボット回避 — Cloudflare、DataDome、PerimeterXでも検知不可能

  • 設定不要 — 1つの環境変数で4つの強力なツールが利用可能

  • スティッキーセッション — 複数のリクエストで同じIPを維持

  • 都市・ISPターゲティング — 必要な時にピンポイントで指定可能

Related MCP server: ProxyBase MCP

⚡ Node.js版 vs Python版 — どちらを選ぶべき？

2種類のMCPサーバーを提供しています。用途に合わせて選択してください：

本リポジトリ (Node.js)

Python版

機能

プロキシルーティング + fetch

高度なアンチボット + ヘッドレスレンダリング + 構造化抽出

用途

シンプルなfetch、地理的ターゲティング

保護されたサイト（Amazon, eBay, LinkedIn）のスクレイピング、JSレンダリングページ

検知対策

Chromeフィンガープリントヘッダー

TLS JA3スプーフィング + Playwrightアンチ検知

インストール

npx proxyclaw-mcp-server

uvx proxyclaw-mcp-server[all]

ツール

4つ (fetch, check_ip, list_countries, rotate)

6つ (+ stealth fetch, render, scrape, extract)

→ Node.js版: 住宅用IPを経由してリクエストをルーティングするだけで十分な場合。

→ Python版: 難易度の高いターゲット（Cloudflare、SPA、Reactサイト）をスクレイピングする場合や、60以上の対応サイトから構造化データを抽出する必要がある場合。

どちらも同じプロキシネットワークを使用しますが、機能のレベルが異なります。

🚀 インストール (30秒)

1. 無料APIキーを取得

iploop.io/signup で登録してください。0.5GBまで無料、クレジットカード不要です。

2. Claude Desktopに追加

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) または %APPDATA%\Claude\claude_desktop_config.json (Windows) を開きます：

{
  "mcpServers": {
    "proxyclaw": {
      "command": "npx",
      "args": ["-y", "proxyclaw-mcp-server"],
      "env": {
        "IPLOOP_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Desktopを再起動してください。これで完了です。

3. 確認

Claudeに以下のように尋ねてください：

"プロキシ経由の出口IPを確認して"

Claudeが proxy_check_ip を呼び出し、経由している住宅用IPを表示します。

🛠️ 利用可能なツール

proxy_fetch

住宅用プロキシ経由で任意のURLをフェッチします。

{
  "url": "https://example.com",
  "country": "US",
  "city": "newyork",
  "session": "my-session-id",
  "timeout": 30
}

用途: 地理的制限のあるサイトのスクレイピング、地域別の価格確認、ボット検知の回避。

proxy_check_ip

現在どのIPと国からアクセスしているかを確認します。

{
  "country": "DE"
}

用途: スクレイピング前にプロキシの場所を確認する際。

proxy_list_countries

利用可能な195カ国以上のリストを表示します。

{}

用途: マダガスカルの2文字コードを正確に知る必要がある場合など。

proxy_rotate

強制的に新しいIPへローテーションします。

{
  "country": "GB"
}

用途: 現在のIPがレート制限を受けた場合に新しいIPが必要な時。

💬 会話例

あなた: "Amazon.comが米国のIPからどう見えるか確認して"

Claude: [country=USを指定してproxy_fetchを呼び出し、HTMLを返す]

あなた: "今度は日本から同じページを確認して"

Claude: [country=JPを指定してproxy_fetchを呼び出し、異なる価格やコンテンツを返す]

あなた: "ルーティング可能な国をすべてリストアップして"

Claude: [proxy_list_countriesを呼び出し、195カ国以上のリストを返す]

あなた: "現在のIPがブロックされた。新しい英国のIPにローテーションして"

Claude: [country=GBを指定してproxy_rotateを呼び出し、新しいIPを確認する]

🔒 セキュリティ

  • APIキーは環境変数経由で渡され、ハードコードされることはありません

  • ターゲットサイトへのすべてのトラフィックはTLS暗号化されます

  • プロキシ認証はプロキシゲートウェイに対してのみプレーンテキストで行われます（他のHTTPプロキシと同様）

  • MCPサーバーによってデータがログ記録や保存されることはありません

📦 高度な設定: ローカルインストール

npm install -g proxyclaw-mcp-server

# Run directly
IPLOOP_API_KEY=your_key proxyclaw-mcp-server

またはDockerを使用する場合:

docker run -e IPLOOP_API_KEY=your_key proxyclaw/mcp-server

🆓 無料枠

  • 0.5 GB の帯域幅が含まれています

  • 195カ国以上すべて利用可能

  • クレジットカード不要

アップグレードはいつでも iploop.io から可能です。

🔗 リンク

Built with ⚡ by IPLoop

Available Tools

4 tools
proxy_check_ipA

Check the current exit IP address and geo-location when routing through the proxy. Useful to verify which country/region your requests are coming from.

ParametersJSON Schema
NameRequiredDescriptionDefault
countryNo2-letter country code to check exit IP from (optional, auto-rotate if omitted)

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. It mentions 'auto-rotate if omitted' which is a key behavioral trait. However, it does not disclose whether the tool is read-only, potential side effects (e.g., token consumption), or error states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, concise and to the point. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple (1 optional param, no output schema). Description covers purpose and key behavior (auto-rotation). Could mention return format (IP, geo) but not critical for a simple check tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (country param described). Description adds context that country is optional and auto-rotation occurs if omitted, which goes beyond schema. However, no other parameters exist, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool checks 'exit IP address and geo-location' and its purpose to 'verify which country/region' the proxy is using. Distinct from siblings like proxy_fetch or proxy_rotate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States when to use: to verify proxy location. Does not explicitly mention when not to use or alternatives, but the context is clear enough. Siblings like proxy_list_countries or proxy_rotate imply alternatives for different needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

proxy_fetchA

Fetch a URL through the ProxyClaw residential proxy network. Routes the request through real residential IPs in 195+ countries. Use for geo-restricted content, anti-bot bypass, or multi-country research.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to fetch (must start with http:// or https://)
countryNo2-letter country code to route through (e.g., US, DE, JP). Auto-rotate if omitted.
cityNoCity name for city-level targeting (optional)
sessionNoSession ID for sticky IP (same IP across requests with same session ID)
asnNoASN number for ISP-level targeting (optional)
timeoutNoRequest timeout in seconds (1-120, default: 30)

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that it routes through residential IPs in 195+ countries, and mentions auto-rotation of IP if no country specified. However, since no annotations are provided, it should also mention potential side effects (e.g., cost, rate limits, IP rotation impact) which are missing. No contradiction with annotations as none exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no wasted words. It is front-loaded with the core action and then adds value with use cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters (100% cover), no output schema, and no annotations, the description covers the main behavioral aspects. It could include a note about response format or potential failures, but overall it provides enough context for a competent agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description does not need to repeat parameter details. The description adds context about country targeting and session stickyness but does not significantly expand beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a URL through a residential proxy network, with specific use cases like geo-restricted content and anti-bot bypass. It distinguishes from siblings like proxy_check_ip (which checks own IP) and proxy_list_countries (which lists countries).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions when to use the tool (geo-restricted content, anti-bot bypass, multi-country research), but does not explicitly state when not to use it or provide alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

proxy_list_countriesA

List all 195+ countries available for routing through the ProxyClaw residential network.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It clearly states the tool returns a list of 195+ countries with routing capability, indicating a read-only operation. However, it does not disclose details like pagination, rate limits, or output format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It conveys the essential purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, no output schema, and performs a straightforward listing operation, the description is nearly complete. It could be improved by explicitly stating the return data structure or confirming it is a read operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, so there is nothing to describe. The description adds value by indicating the tool lists all countries without need for input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and resource ('countries available for routing through the ProxyClaw residential network'), and clearly distinguishes the tool from its siblings (e.g., proxy_check_ip, proxy_fetch, proxy_rotate) by its unique purpose of listing countries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies that the tool is meant to retrieve a list of all supported countries for routing, but does not explicitly state when to use it over alternatives. Provides no guidance on prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

proxy_rotateA

Force IP rotation by fetching with a new random session. Returns the new exit IP to confirm rotation worked.

ParametersJSON Schema
NameRequiredDescriptionDefault
countryNo2-letter country code (optional)

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description discloses that the tool forces rotation and returns the new IP, which is sufficient behavioral context. However, it does not mention any side effects like invalidating existing sessions or rate limits. Since no annotations are provided, the description carries full burden, but it adequately covers the core behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste: states what it does and what it returns. Optimal for the tool's simplicity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given low complexity (1 optional param, no output schema, no nested objects), the description is sufficiently complete. It covers purpose, action, and outcome. Minor gap is lack of explicit statement about any prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one optional parameter with 100% schema coverage; description does not add meaning beyond schema's '2-letter country code (optional).' Baseline 3 is appropriate as schema already explains the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool's action ('force IP rotation'), method ('fetching with a new random session'), and outcome ('returns the new exit IP to confirm rotation'). It is distinct from siblings like proxy_check_ip which checks current IP, and proxy_fetch which likely fetches a page.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies when to use (when a new IP is needed) and provides confirmation mechanism. It does not explicitly state when not to use or mention alternatives, but the purpose is self-evident given sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.0
    • First observedproxy_check_ip
    • First observedproxy_fetch
    • First observedproxy_list_countries
    • First observedproxy_rotate
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: check IP, fetch URL, list countries, and rotate IP. There is no overlap between these functions.

Naming Consistency5/5

All tools follow a consistent 'proxy_verb' pattern (e.g., proxy_check_ip, proxy_fetch), making them easy to understand and remember.

Tool Count5/5

The set of 4 tools covers the core proxy operations (check, fetch, list, rotate) without unnecessary extras, well-scoped for the proxy domain.

Completeness4/5

Core proxy workflows are covered: checking IP, fetching through proxy, listing countries, and rotating IP. One minor gap might be the lack of a tool to set the country explicitly, but rotation and checks suffice.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Proxy4Agent

    Goldentrii
    A
    license
    Not graded
    quality
    C
    maintenance
    Routes AI agent HTTP requests through residential proxies to bypass anti-bot systems, geo-target by country/city, and maintain sticky sessions across multi-step workflows.
    17 npm
    1
    MIT
  • quantumproxies-mcp by quantumproxies

    quantumproxies-mcpofficial

    quantumproxies
    A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to scrape, search, map, and crawl the web through residential proxies with real-browser TLS fingerprints, and to generate ready-to-use proxy endpoints of various types for any HTTP client.
    25
    21 npm
    MIT