LangGraph MCP Agents
LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP tools.
What is LangGraph MCP Agents?
LangGraph MCP Agents is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to langgraph-powered react agent with model context protocol (mcp) integration. a streamlit web interface for dynamically configuring, deploying, and interacting with ai agents capable of accessing vario...
LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP tools.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- LangGraph-powered ReAct agent with Model Context Protocol (M
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx langgraph-mcp-agentsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LangGraph MCP Agents
LangGraph MCP Agents is a Streamlit-based web interface for deploying LangGraph ReAct agents that can dynamically access external tools and data sources through the Model Context Protocol. It integrates with LangChain's MCP adapters to let you add, remove, and configure MCP tool servers through a UI without restarting the application. Ideal for developers who want a visual, conversational environment for experimenting with multi-tool AI agents powered by Claude or OpenAI models.
Prerequisites
- Python 3.12 or higher installed
- Docker Desktop (for the recommended Docker-based setup) or uv package manager for source installs
- An Anthropic API key (for Claude models) and/or an OpenAI API key (for GPT models)
- Optional: LangSmith API key for agent tracing and observability
- An MCP client such as Claude Desktop or a compatible MCP host
Clone the repository
Clone the LangGraph MCP Agents repository from GitHub to your local machine.
git clone https://github.com/teddynote-lab/langgraph-mcp-agents.git
cd langgraph-mcp-agentsCreate your environment file
Copy the example environment file and fill in your API keys. At minimum, provide one LLM provider key (ANTHROPIC_API_KEY or OPENAI_API_KEY). LangSmith keys are optional but useful for tracing.
cp .env.example .env
# Edit .env with your keys:
# ANTHROPIC_API_KEY=your_anthropic_api_key
# OPENAI_API_KEY=your_openai_api_key
# LANGSMITH_API_KEY=your_langsmith_api_key
# LANGSMITH_TRACING=true
# LANGSMITH_ENDPOINT=https://api.smith.langchain.com
# LANGSMITH_PROJECT=LangGraph-MCP-AgentsStart the application with Docker Compose
Run the appropriate Docker Compose command for your CPU architecture. The application will be available at http://localhost:8585.
# AMD64/x86_64 (Intel/AMD):
docker compose -f docker-compose.yaml up -d
# ARM64 (Apple Silicon M1/M2/M3/M4):
docker compose -f docker-compose-mac.yaml up -dInstall from source with uv (alternative to Docker)
If you prefer running without Docker, create a virtual environment, install dependencies with uv, and launch the Streamlit app directly.
uv venv
uv pip install -r requirements.txt
source .venv/bin/activate
streamlit run app.pyAdd MCP tool servers via the UI
Open http://localhost:8585 in your browser. Use the tool management panel to add MCP servers (Smithery JSON format is supported). Tools are loaded dynamically without restarting the application.
Select a model and start chatting
Choose your preferred LLM (claude-3-7-sonnet-latest, gpt-4o, etc.) from the UI dropdown, then interact with the ReAct agent. The streaming response panel shows tool calls and reasoning steps in real time.
LangGraph MCP Agents Examples
Client configuration
This project runs as a standalone Streamlit app rather than as a Claude Desktop MCP server. To integrate with Claude Desktop, configure it to run the server via stdio using Python.
{
"mcpServers": {
"langgraph-mcp-agents": {
"command": "python",
"args": ["path/to/langgraph-mcp-agents/src/server.py"],
"env": {
"ANTHROPIC_API_KEY": "your_anthropic_api_key",
"OPENAI_API_KEY": "your_openai_api_key"
}
}
}
}Prompts to try
Once running with MCP tools connected, try these prompts in the Streamlit chat interface:
- "Search the web for the latest news on LangGraph and summarize the top 3 results"
- "Use the filesystem tool to list files in my project directory and explain the structure"
- "Fetch the content from https://example.com and extract all headings"
- "Run a calculation using the math tool and show me the steps"Troubleshooting LangGraph MCP Agents
Docker container fails to start or port 8585 is already in use
Edit docker-compose.yaml to change the host port mapping (e.g., '8586:8585') before running docker compose up. Alternatively, stop other services using port 8585 with: lsof -i :8585 && kill -9 <PID>.
LLM API calls fail with authentication errors
Verify your .env file is in the project root directory (not inside the dockers/ folder) and that the API key values don't have extra quotes or spaces. Run 'docker compose down && docker compose up -d' to reload environment variables.
MCP tools added in the UI don't appear or don't work
Ensure the MCP server JSON you paste matches the Smithery JSON format exactly. Check the tool server is running and accessible from inside the Docker container. For local stdio servers, you may need to mount the host filesystem into the container.
Frequently Asked Questions about LangGraph MCP Agents
What is LangGraph MCP Agents?
LangGraph MCP Agents is a Model Context Protocol (MCP) server that langgraph-powered react agent with model context protocol (mcp) integration. a streamlit web interface for dynamically configuring, deploying, and interacting with ai agents capable of accessing various data sources and apis through mcp tools. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LangGraph MCP Agents?
Follow the installation instructions on the LangGraph MCP Agents GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LangGraph MCP Agents?
LangGraph MCP Agents works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LangGraph MCP Agents free to use?
Yes, LangGraph MCP Agents is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LangGraph MCP Agents Alternatives — Similar Coding Agents Servers
Looking for alternatives to LangGraph MCP Agents? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LangGraph MCP Agents in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LangGraph MCP Agents?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.