Simple CLI MCP Client Using LangChain / Python
@hideya
基本情報
Simple CLI MCP Client Using LangChain / Python について
Simple CLI MCP Client Implementation Using LangChain ReAct Agent / Python
概要
What is Simple CLI MCP Client Using LangChain / Python?
A command‑line application that demonstrates how to use Model Context Protocol (MCP) server tools via the LangChain ReAct Agent. It runs on Python 3.11+ and is aimed at developers integrating MCP with LangChain.
How to use Simple CLI MCP Client Using LangChain / Python?
Install dependencies with make install, copy .env.template to .env and populate API keys for Anthropic, OpenAI, and/or Groq. Configure LLM and MCP servers in llm_mcp_config.json5 (JSON5 format with environment variable substitution). Run with make start; press Enter at the prompt to use built‑in example queries that invoke MCP tools.
Key features of Simple CLI MCP Client Using LangChain / Python
- Converts MCP tools into LangChain‑compatible
BaseToolobjects viaconvert_mcp_to_langchain_tools() - Supports parallel initialization of multiple MCP servers
- Works with LLMs from Anthropic, OpenAI, and Groq
- Config file uses JSON5 (comments, trailing commas) and
${...}env variable substitution - Includes configurable example queries for quick testing
Use cases of Simple CLI MCP Client Using LangChain / Python
- Prototype a LangChain ReAct agent that calls MCP‑exposed tools
- Test MCP server integration without a full IDE or desktop app
- Compare tool‑calling behavior across different LLM providers
- Automate CLI workflows that chain multiple MCP tool invocations
FAQ from Simple CLI MCP Client Using LangChain / Python
What is the Model Context Protocol (MCP)?
MCP is an open protocol that standardises how applications provide context and tools to LLMs. This client connects to MCP servers and exposes their tools to a LangChain agent.
Which LLM providers are supported?
Anthropic, OpenAI, and Groq are currently supported. You must provide the corresponding API keys in .env.
How does the config file differ from Claude for Desktop’s?
The configuration follows the same structure as Claude for Desktop’s mcpServers, but the key name is changed to mcp_servers (snake_case) to match JSON conventions.
How do I set up API keys?
Copy .env.template to .env, then fill in the keys. The .gitignore already excludes .env to prevent accidental commits. Use ${KEY_NAME} in the JSON5 config to reference environment variables.
Is there a TypeScript version?
Yes, a TypeScript version of this MCP client is available here.
What is the license?
The project is released under the MIT License.
「エージェントフレームワーク」の他のクライアント
Nerve
evilsocketThe Simple Agent Development Kit.
SSE-based Server and Client for
sidharthrajaramA working pattern for SSE-based MCP clients and servers
Unified MCP Client Library
pietrozullomcp-use is the easiest way to interact with mcp servers with custom agents
Saiki
truffle-aiA customizable, general purpose AI Agent that supports MCP. Talk to Saiki in natural language to control computers, applications and more!
コメント