LangChain Anthropic

Provides LangChain + Anthropic Claude MCP tools to build production-ready RAG systems, vector stores, and document ingestion workflows.

typescript

0

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "spencer-life-langchain-anthropic-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "spencer-life/langchain-anthropic-mcp-server"
      ]
    }
  }
}

You can run the LangChain Anthropic MCP Server to expose LangChain and Anthropic Claude capabilities as MCP tools. This enables you to quickly wire production-ready retrieval-augmented generation workflows, vector stores, document ingestion pipelines, and more, with MCP clients like Cursor.

How to use

Once the MCP server is running, you interact with it through your MCP client. You can ask your AI assistant to perform tasks such as setting up a Supabase vector store, creating a RAG chain with Claude, or generating code for document ingestion. The server exposes a suite of tools that you can invoke from your MCP-enabled assistant, enabling end-to-end production workflows without leaving your chat or automation surface.

How to install

Prerequisites you need before starting:

Node.js installed on your machine (v14+ recommended). You should also have npm available.

Steps to install and run the MCP server

# Install prerequisites if needed (check your package manager and node installation method)

# Run the MCP server using npx (this pulls the package and starts the MCP server)
npx -y spencer-life/langchain-anthropic-mcp-server

Configure your MCP client to use the server

If you use an MCP client like Cursor, add the server to your client configuration with the following snippet. This starts the server via npx and registers it under a short name you can reference from your prompts.

{
  "mcpServers": {
    "langchain-anthropic": {
      "command": "npx",
      "args": [
        "-y",
        "spencer-life/langchain-anthropic-mcp-server"
      ],
      "env": {}
    }
  }
}

Notes on usage

You can reference supported tools by name in your prompts, for example asking to set up a Supabase vector store or to create a RAG chain with Claude Sonnet.

Available tools

setup_supabase_vectorstore

Complete setup for a Supabase vector store including schema, credentials handling, and index creation.

create_rag_chain

Assemble a fully functioning RAG chain with Claude, including retriever configuration and prompt design.

generate_document_ingestion

Generate code for document loading and chunking to feed the vector store.

create_conversational_rag

Set up a conversational RAG workflow with memory across interactions.

setup_hybrid_search

Configure a hybrid search that combines vector retrieval with keyword search.

create_multi_query_retriever

Provide multi-query retrieval to improve recall across queries.

setup_extended_thinking

Enable extended thinking configurations to enhance reasoning during processing.

generate_package_setup

Produce complete dependency lists and setup instructions for the MCP workflow.