LangChain adapter for MCP tools
## LangChain MCP Server: LLM Application Framework The **LangChain MCP Server** integrates the leading framework for building LLM-powered applications into Google Antigravity. LangChain provides the building blocks for chains, agents, and retrieval systems that form the foundation of modern AI applications. ### Why LangChain MCP? LangChain simplifies LLM application development: - **Composable**: Chain together components easily - **Model Agnostic**: Works with any LLM provider - **Rich Ecosystem**: 500+ integrations available - **Agent Framework**: Build autonomous AI agents - **Production Ready**: LangServe for deployment ### Key Features #### 1. Chain Composition ```python from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate from langchain_core.output_parsers import StrOutputParser llm = ChatOpenAI(model="gpt-4-turbo") prompt = ChatPromptTemplate.from_template("Explain {topic} simply") parser = StrOutputParser() # Compose chain using pipe operator chain = prompt | llm | parser result = chain.invoke({"topic": "machine learning"}) print(result) ``` #### 2. RAG Pipeline ```python from langchain_community.vectorstores import Chroma from langchain_openai import OpenAIEmbeddings from langchain.chains import RetrievalQA # Create vector store vectorstore = Chroma.from_documents(documents, OpenAIEmbeddings()) # Build RAG chain qa_chain = RetrievalQA.from_chain_type( llm=ChatOpenAI(), retriever=vectorstore.as_retriever(), return_source_documents=True ) result = qa_chain.invoke({"query": "What is our refund policy?"}) ``` #### 3. Agents ```python from langchain.agents import create_react_agent, AgentExecutor from langchain.tools import Tool tools = [ Tool(name="search", func=search_web, description="Search the web"), Tool(name="calculate", func=calculator, description="Do math") ] agent = create_react_agent(llm, tools, prompt) executor = AgentExecutor(agent=agent, tools=tools) result = executor.invoke({"input": "What is 25% of Tesla stock price?"}) ``` ### Configuration ```json { "mcpServers": { "langchain": { "command": "npx", "args": ["-y", "@anthropic/mcp-langchain"], "env": { "OPENAI_API_KEY": "your-key", "LANGCHAIN_TRACING_V2": "true" } } } } ``` ### Use Cases **Chatbots**: Build conversational AI with memory and context management. **RAG Systems**: Create question-answering systems over private data. **Autonomous Agents**: Build agents that can reason and use tools. The LangChain MCP Server brings LLM application building blocks to Antigravity.
{
"mcpServers": {
"langchain": {
"mcpServers": {
"langchain": {
"args": [
"install",
"langchain-mcp-adapters"
],
"command": "pip"
}
}
}
}
}