What dependencies are required?
Requires AdsPower installed, Python 3.10 or higher, and uv for package management.
@AdsPower
基本情報
MCP server for using the AdsPower LocalAPI
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"local-api-mcp-python": {
"command": "uv",
"args": [
"venv"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
It is a Model Context Protocol server that interfaces with the AdsPower browser LocalAPI. It enables LLMs to start browsers, create browsers, and update browser fingerprint configurations. It is for developers using LLM tools like Claude Desktop or Cursor.
Install AdsPower, Python 3.10 or higher, and uv. Clone the repository, set up a virtual environment, and install dependencies with uv pip install .. Then add the server configuration to Claude Desktop’s config file (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json; Windows: %APPDATA%/Claude/claude_desktop_config.json) using the provided JSON snippet. Invoke the server by asking the LLM natural language commands, for example: “Create an Android UA browser using Chrome 134.”
Requires AdsPower installed, Python 3.10 or higher, and uv for package management.
Clone the repo, install dependencies with uv, then add the server configuration to Claude Desktop’s config file pointing to the project directory.
Use LLMs to start browsers, create new browsers, and update browser fingerprint configurations.
The README shows usage with Claude Desktop and Cursor, so it likely works with any MCP‑compatible client.
By asking the LLM natural language commands, e.g., “Create an Android UA browser using Chrome 134.”

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

Hermoso is an AI marketing agent and AI ad generator you run from your AI agent: a remote MCP server that researches the ads already winning in your market, makes image and video ads and organic posts in your brand, publ

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント