LangChain RAG MCP Boilerplate
Boilerplate to create Develop Agents with RAG, MCP, Tools, VectorDB, Memory
What is LangChain RAG MCP Boilerplate?
LangChain RAG MCP Boilerplate is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to boilerplate to create develop agents with rag, mcp, tools, vectordb, memory
Boilerplate to create Develop Agents with RAG, MCP, Tools, VectorDB, Memory
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Boilerplate to create Develop Agents with RAG, MCP, Tools, V
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agent-langchain-rag-mcp-tools-boilerplateConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LangChain RAG MCP Boilerplate
LangChain RAG MCP Boilerplate is a full-stack reference architecture for building AI agents that combine Retrieval-Augmented Generation, vector database memory, web search, and MCP tool integration. It provides a FastAPI backend with a LangGraph multi-agent orchestrator and a React frontend, giving developers a production-ready starting point for custom AI assistants.
Prerequisites
- Python 3.10 or later with pip
- Node.js 18 or later with npm
- OpenAI API key (GPT-4o is used by default for LLM inference)
- Git installed
- A running Qdrant instance (local Docker or cloud) for vector storage and semantic cache
Clone the repository and set up the Python backend
Clone the boilerplate repo, create a virtual environment, install Python dependencies, and copy the example environment file.
git clone https://github.com/jadenitishraj/Agent-langchain-rag-mcp-tools-boilerplate.git
cd Agent-langchain-rag-mcp-tools-boilerplate
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .envConfigure environment variables
Edit the .env file and set your OpenAI API key. Optionally configure the Qdrant URL and Brave Search API key if you want live web search.
# .env
OPENAI_API_KEY=sk-your-openai-key-here
# Optional
QDRANT_URL=http://localhost:6333
BRAVE_SEARCH_API_KEY=your-brave-keyIndex your documents for RAG
Run the indexing script to embed your codebase or documents into the Qdrant vector database so the RAG agent can retrieve them.
python scripts/index_codebase.pyInstall frontend dependencies
Navigate to the frontend directory and install Node.js dependencies.
cd frontend
npm installStart the backend and frontend
Run the FastAPI backend and the Vite React frontend in separate terminals. The backend starts on port 8000 and the frontend on port 5173.
# Terminal 1 - Backend
uvicorn main:app --reload --port 8000
# Terminal 2 - Frontend
cd frontend
npm run devAdd custom tools
Create a new tool file in the tools/ directory using the @tool decorator from LangChain, then register it in tools/__init__.py under ALL_TOOLS. The agent will auto-detect it on next startup.
# tools/my_tool.py
from langchain.tools import tool
@tool
def my_custom_tool(input: str) -> str:
"""Description of what this tool does."""
return f"Result for: {input}"
# tools/__init__.py — add to ALL_TOOLS list
from .my_tool import my_custom_tool
ALL_TOOLS = [..., my_custom_tool]LangChain RAG MCP Boilerplate Examples
Client configuration
The boilerplate runs as a standalone web app rather than a Claude Desktop MCP server. Access it at http://localhost:5173 after starting both processes.
{
"backend": "http://localhost:8000",
"frontend": "http://localhost:5173",
"agents": [
"history_agent",
"rag_agent",
"memory_agent",
"web_agent"
],
"vectordb": "qdrant",
"llm": "gpt-4o"
}Prompts to try
Example questions to ask the agent via the web UI once the backend and frontend are running.
- "Summarize what you know about the project structure based on the codebase"
- "Search the web for the latest LangChain release notes"
- "Remember that my preferred output format is markdown tables"
- "What did we discuss in our previous conversation about API design?"
- "Find all functions related to authentication in the indexed codebase"
- "Add a new tool that calls the OpenWeatherMap API and explain how to register it"Troubleshooting LangChain RAG MCP Boilerplate
RAG agent returns no results after indexing
Confirm Qdrant is running at the URL specified in QDRANT_URL. Run docker run -p 6333:6333 qdrant/qdrant if using Docker. Re-run python scripts/index_codebase.py after Qdrant is reachable.
Semantic cache returns wrong answers for new questions
The semantic cache uses a similarity threshold of 0.70. If cached responses are too aggressively matched, raise this threshold in the cache configuration in langraph/agent.py.
Frontend cannot reach the backend API
Ensure the backend is running on port 8000 and that CORS is enabled for localhost:5173. Check the backend terminal for startup errors and verify the uvicorn command completed without errors.
Frequently Asked Questions about LangChain RAG MCP Boilerplate
What is LangChain RAG MCP Boilerplate?
LangChain RAG MCP Boilerplate is a Model Context Protocol (MCP) server that boilerplate to create develop agents with rag, mcp, tools, vectordb, memory It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LangChain RAG MCP Boilerplate?
Follow the installation instructions on the LangChain RAG MCP Boilerplate GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LangChain RAG MCP Boilerplate?
LangChain RAG MCP Boilerplate works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LangChain RAG MCP Boilerplate free to use?
Yes, LangChain RAG MCP Boilerplate is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LangChain RAG MCP Boilerplate Alternatives — Similar Coding Agents Servers
Looking for alternatives to LangChain RAG MCP Boilerplate? 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 LangChain RAG MCP Boilerplate 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 LangChain RAG MCP Boilerplate?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.