What is the difference between apps-server and unified-server?
apps-server provides direct access to tools from specified apps (e.g., Gmail). unified-server gives two meta functions to discover and execute all functions available on ACI.dev.
@aipotheosis-labs
基本信息
MCP server(s) for Aipolabs ACI.dev
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"aci-mcp": {
"command": "uvx",
"args": [
"aci-mcp",
"--help"
]
}
}
}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。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
An MCP server package providing two servers (apps-server and unified-server) for accessing ACI.dev managed functions (tools) via the Model Context Protocol. Designed for developers integrating ACI.dev capabilities into MCP-compatible clients.
Install via uvx and run either aci-mcp apps-server or aci-mcp unified-server. Configure with --linked-account-owner-id and optionally --apps (for apps-server). Require ACI_API_KEY as environment variable. Also supports Docker deployment.
apps-server provides direct access to tools from specified apps (e.g., Gmail). unified-server gives two meta functions to discover and execute all functions available on ACI.dev.
Install uv, then run `uvx aci-mcp apps-server --apps APP1,APP2 --linked-account-owner-id ID` or `uvx aci-mcp unified-server --linked-account-owner-id ID`.
Yes. Build the image with `docker build -t aci-mcp .` and run with environment variables for API key and account owner ID.
Use the MCP inspector (`npx @modelcontextprotocol/inspector`) or check logs at `~/Library/Logs/Claude/mcp*.log`.
Yes, you must provide an ACI_API_KEY environment variable when running the server (shown in Docker commands and expected by both servers).

Model Context Protocol Servers
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Open-source MCP to use Blender with any LLM
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns
评论