",{"name":"viewport","content":"width=device-width, initial-scale=1"}]] b:null 28:I[60719,["7626","static/chunks/f6ab4fea-4425dae3da7674a3.js","8548","static/chunks/b27dc69b-e5acb70cd9d66ddf.js","5232","static/chunks/5232-db5923cda78a4960.js","6465","static/chunks/6465-6b79f1dc957ae3f4.js","9388","static/chunks/9388-d1a745fd53a10850.js","4902","static/chunks/4902-40271c136eb736f1.js","1508","static/chunks/1508-abbc58115cbb4fd0.js","6125","static/chunks/6125-6f7cbc86df4f2503.js","7771","static/chunks/7771-66979ce602088329.js","7660","static/chunks/7660-f5d56ac6a9ee6cc8.js","4147","static/chunks/4147-ef3df161a800b88b.js","9783","static/chunks/9783-e1d5b54e9718b38b.js","8084","static/chunks/8084-f1229cc5d0501fe0.js","2024","static/chunks/2024-e03e13f5faa34f45.js","7796","static/chunks/app/%5Blocale%5D/(default)/server/%5Bname%5D/%5Bauthor_name%5D/page-c3a3facf548ee943.js"],"default"] 29:T12d8,

ACP to MCP Adapter

**Connect ACP Agents to MCP Applications Seamlessly** [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-License-EA7826?style=plastic&logo=apache&logoColor=white)](https://github.com/i-am-bee/beeai-framework?tab=Apache-2.0-1-ov-file#readme) [![Follow on Bluesky](https://img.shields.io/badge/Follow%20on%20Bluesky-0285FF?style=plastic&logo=bluesky&logoColor=white)](https://bsky.app/profile/beeaiagents.bsky.social) [![Join our Discord](https://img.shields.io/badge/Join%20our%20Discord-7289DA?style=plastic&logo=discord&logoColor=white)](https://discord.com/invite/NradeA6ZNF) [![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-0072C6?style=plastic&logo=linuxfoundation&logoColor=white)](https://lfaidata.foundation/projects/)

The **ACP to MCP Adapter** is a lightweight standalone server that acts as a bridge between two AI ecosystems: **Agent Communication Protocol (ACP)** for agent-to-agent communication and **Model Context Protocol (MCP)** for connecting AI models to external tools. It allows MCP applications (like **Claude Desktop**) to discover and interact with ACP agents as resources. ## Capabilities & Tradeoffs This adapter enables interoperability between ACP and MCP with specific benefits and tradeoffs: ### Benefits - Makes ACP agents discoverable as MCP resources - Exposes ACP agent runs as MCP tools - Bridges two ecosystems with minimal configuration ### Current Limitations - ACP agents become MCP tools instead of conversational peers - No streaming of incremental updates - No shared memory across servers - Basic content translation between formats without support for complex data structures This adapter is best for situations where you need ACP agents in MCP environments and accept these compromises. ## Requirements - Python 3.11 or higher - Installed Python packages: `acp-sdk`, `mcp` - An ACP server running (Tip: Follow the [ACP quickstart](https://github.com/i-am-bee/acp/blob/main/README.md#quickstart) to start one easily) - An MCP client application (We use [Claude Desktop](https://claude.ai/download) in the quickstart) ## Quickstart **1. Run the Adapter** Start the adapter and connect it to your ACP server: ```sh uvx acp-mcp http://localhost:8000 ``` > [!NOTE] > Replace `http://localhost:8000` with your ACP server URL if different.

Prefer Docker?

```sh docker run -i --rm ghcr.io/i-am-bee/acp-mcp http://host.docker.internal:8000 ``` **Tip:** `host.docker.internal` allows Docker containers to reach services running on the host (adjust if needed for your setup).

**2. Connect via Claude Desktop** To connect via Claude Desktop, follow these steps: 1. Open the Claude menu on your computer and navigate to Settings (note: this is separate from the in-app Claude account settings). 2. Navigate to Developer > Edit Config 3. The config file will be created here: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` 4. Edit the file with the following: ```json { "mcpServers": { "acp-local": {

ACP to MCP Adapter

Tools