mcp-agent-tool-adapter

What is mcp-agent-tool-adapter?

mcp-agent-tool-adapter enables modular tool invocation via the MCP protocol and transforms MCP tools into agents using either Google ADK (with FastAPI or CLI interfaces) or LangGraph (with ReAct and streaming tool planning). It is designed for developers who want to connect MCP-compatible tools to agent frameworks.

How to use mcp-agent-tool-adapter?

Clone the repository, install dependencies with pip install -r requirements.txt, define tools in mcp_config.json, then run either python app_client_adk.py for a Google ADK CLI agent or python app_client_langgraph.py for a LangGraph ReAct CLI agent.

Key features of mcp-agent-tool-adapter

• Transforms MCP tools into Google ADK or LangGraph agents.
• Supports streaming interfaces via FastAPI or CLI.
• Handles tool server spawning, session management, and cleanup.
• Dynamically swap agent type by changing tool_type to "google" or "langgraph".
• Modular MCPClient architecture for tool adaptation.

Use cases of mcp-agent-tool-adapter

• Building a CLI chat agent that uses MCP filesystem tools.
• Creating a LangGraph ReAct agent with streaming tool planning.
• Prototyping multi-agent workflows that switch between ADK and LangGraph.
• Exposing MCP tools as FastAPI endpoints via Google ADK agents.

FAQ from mcp-agent-tool-adapter

What MCP servers does mcp-agent-tool-adapter support?

Any MCP server defined in mcp_config.json; an example uses the @modular-protocol/filesystem server via npx.

How do I change the agent type?

Set tool_type to "google" for Google ADK or "langgraph" for LangGraph in your application code.

What are the runtime requirements?

Python 3.10 or higher is required.

Does mcp-agent-tool-adapter support streaming?

Yes, both the Google ADK and LangGraph agents include streaming capabilities (FastAPI or CLI).

Is there a CLI interface?

Yes, two CLI scripts are provided: app_client_adk.py and app_client_langgraph.py.