Examples

Each example walks you through building something real on Kapa from start to finish: you pick one, follow the steps, and end with a working result. They assume you have completed Getting started, so a project with an indexed source already exists. Once your build is working, Tune retrieval size and Prompt for grounded answers show how to improve its answers.

Add knowledge base search to a LangChain agentGive a LangChain agent access to your documentation via a hosted MCP server

Add documentation search to your MCP serverServe documentation search from the MCP server you already ship

Connect internal knowledge to ChatGPT and ClaudeLet your team ask about company knowledge inside the assistant they already use

Answer GitHub issues automaticallyA GitHub Action posts a documentation-grounded first reply on every new issue

Draft replies for your support team in Intercom FinA drafted, knowledge-grounded reply on every new conversation, as an internal note

Make Intercom Fin better at handling large and complex knowledge basesConnect everything you index in Kapa to Fin as a Custom MCP data connector

Give your n8n agent access to your knowledge without a RAG pipelineOne MCP Client Tool node replaces the vector store, embeddings, and chunking pipeline

Draft replies for your support team in FrontA drafted, knowledge-grounded reply on every new conversation, as a comment for review

Draft replies for your support team in ZendeskA drafted, knowledge-grounded reply on every new ticket, as an internal comment