What dependencies are required?
Requires AdsPower installed, Python 3.10 or higher, and uv for package management.
@AdsPower
基本信息
MCP server for using the AdsPower LocalAPI
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"local-api-mcp-python": {
"command": "uv",
"args": [
"venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
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.”

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
评论