From Protocol to Intelligence: Powering Agents with MCP.
MCP Agent Tool Adapter enables modular tool invocation via the MCP protocol, and provides agents that can dynamically reason with tools using either Google ADK or LangGraph.
This project transforms MCP tools into:
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
# 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
❯ python app_client_adk.py
❯ python app_client_langgraph.py
Ensure your mcp_config.json
defines tools like:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["@modular-protocol/filesystem"]
}
}
}
MCP tools are connected to agents through MCPClient
, which handles:
You can dynamically swap agent type by changing tool_type
to "google"
or "langgraph"
in your app.
We welcome contributions in:
This project is licensed under the MIT License.For more details, refer to the LICENSE file.
{
"mcpServers": {
"filesystem": {
"env": {},
"args": [
"@modular-protocol/filesystem"
],
"command": "npx"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.