224fdfa35.js","1358","static/chunks/1358-51104e2af656c119.js","2439","static/chunks/app/%5Blocale%5D/(default)/tag/%5Bname%5D/page-e01bef69b5169e46.js"],"PageTitleTabs"] 23:I[85939,["7626","static/chunks/f6ab4fea-4425dae3da7674a3.js","5232","static/chunks/5232-db5923cda78a4960.js","6465","static/chunks/6465-6b79f1dc957ae3f4.js","9388","static/chunks/9388-d1a745fd53a10850.js","9732","static/chunks/9732-8158987224fdfa35.js","1358","static/chunks/1358-51104e2af656c119.js","2439","static/chunks/app/%5Blocale%5D/(default)/tag/%5Bname%5D/page-e01bef69b5169e46.js"],"default"] 2a:I[41664,["7626","static/chunks/f6ab4fea-4425dae3da7674a3.js","5232","static/chunks/5232-db5923cda78a4960.js","6465","static/chunks/6465-6b79f1dc957ae3f4.js","9388","static/chunks/9388-d1a745fd53a10850.js","9732","static/chunks/9732-8158987224fdfa35.js","1358","static/chunks/1358-51104e2af656c119.js","2439","static/chunks/app/%5Blocale%5D/(default)/tag/%5Bname%5D/page-e01bef69b5169e46.js"],"Pagination"] 24:Td4f,

mcp-agent-tool-adapter

From Protocol to Intelligence: Powering Agents with MCP.

repo-top-language repo-language-count

--- ## 📍 Overview **MCP Agent Tool Adapter** enables modular tool invocation via the [MCP protocol](https://github.com/modelcontextprotocol), and provides agents that can dynamically reason with tools using either [Google ADK](https://github.com/google/adk-python) or [LangGraph](https://github.com/langchain-ai/langgraph). This project transforms MCP tools into: - 🤖 Google ADK-based agents with streaming FastAPI or CLI interfaces - 🧠 LangGraph-based agents that use ReAct + streaming tool planning --- ## 🧱 Project Structure ```bash mcp-agent-tool-adapter/ ├── mcp_client/ # Core client implementation (modular) │ ├── client.py # MCPClient & MCPServer │ ├── tool_loader.py # High-level async loader │ └── types.py # Shared type definitions ├── app_client_adk.py # Google ADK agent + CLI chat ├── app_client_langgraph.py # LangGraph agent + ReAct CLI chat ├── mcp_config.json # Example MCP tool config ├── requirements.txt # Dependencies └── README.md ``` --- ## 🚀 Getting Started ### ☑️ Prerequisites - Python 3.10+ ### ⚙️ Installation ```bash # Clone this repository ❯ git clone https://github.com/serkanyasr/mcp-agent-tool-adapter ❯ cd mcp-agent-tool-adapter # Install dependencies ❯ pip install -r requirements.txt ``` --- ## 🤖 Usage ### Run Google ADK CLI agent: ```bash ❯ python app_client_adk.py ``` ### Run LangGraph ReAct CLI agent: ```bash ❯ python app_client_langgraph.py ``` Ensure your `mcp_config.json` defines tools like: ```json { "mcpServers": { "filesystem": { "command": "npx", "args": ["@modular-protocol/filesystem"] } } } ``` --- ## 🧠 Tool Architecture MCP tools are connected to agents through `MCPClient`, which handles: - Tool server spawning (via subprocess) - Session management - Tool adaptation (langgraph or Google ADK) - Cleanup You can dynamically swap agent type by changing `tool_type` to `"google"` or `"langgraph"` in your app. --- ## 🧪 Development / Contributing - Fork the repo and create feature branches. - Submit a PR with a description of your changes. - Tag @serkanyasr in issues or PRs. We welcome contributions

#google-adk

mcp-agent-tool-adapter

MCP Space 🚀

Gofannon