langgraph-mcp-agents

MCP.Pizza Chef: braincrew-lab

Rather than using someone else's chat app, you run this one on your own machine: a simple web page where you paste in the tools you want, apply them, and start asking questions. Every tool call shows up as it happens, and the conversation history is kept. It starts through Docker or Python, needs a key from OpenAI or Anthropic to power the replies, and can sit behind a simple login. The project has not been updated since April 2025.

Unmaintained · no updates since April 2025
Coding
Other

Use This MCP client To

Try out a new tool before wiring it into anything Watch exactly which tools an assistant reaches for Run a private chat assistant on my own machine Swap tools in and out without restarting the app Put a simple login in front of a shared assistant

README

LangGraph Agents + MCP

English Korean

GitHub License Python Version

project demo

Project Overview

project architecture

LangChain-MCP-Adapters is a toolkit provided by LangChain AI that enables AI agents to interact with external tools and data sources through the Model Context Protocol (MCP). This project provides a user-friendly interface for deploying ReAct agents that can access various data sources and APIs through MCP tools.

Features

  • Streamlit Interface: A user-friendly web interface for interacting with LangGraph ReAct Agent with MCP tools
  • Tool Management: Add, remove, and configure MCP tools through the UI (Smithery JSON format supported). This is done dynamically without restarting the application
  • Streaming Responses: View agent responses and tool calls in real-time
  • Conversation History: Track and manage conversations with the agent

langgraph-mcp-agents FAQ

Is this something I add to Claude?
No, it is the other side of the arrangement — a chat app of your own that other tools plug into.
Do I need a paid key?
Yes. Replies come from OpenAI or Anthropic models, so you supply your own key for whichever you choose.
How hard is setup?
Developer level. You install Docker or Python, copy an example settings file and start the app yourself.
Can I use this to test a tool I found on Smithery?
Yes — copy the settings shown on Smithery, paste them into the sidebar and hit apply.
Is it still maintained?
The repository has had no updates since April 2025, so treat it as a working demo rather than a supported product.
Where does it run?
In your browser at a local address after you start it, not on anybody else's servers.