Haiku MCP Server

Agentic Retrieval Augmented Generation (RAG) with LanceDB

Local serverstdioPython

What is the Haiku MCP server?

Agentic Retrieval Augmented Generation (RAG) with LanceDB. The haiku mcp server wraps that behind the Model Context Protocol, so an assistant can use it rather than through you.

What it actually does

Includes all features: document processing, all embedding providers, and rerankers.

  • Hybrid search — — Vector + full-text with Reciprocal Rank Fusion
  • Multimodal & cross-modal search — — Multimodal embedders (vLLM, VoyageAI, Cohere) put picture vectors in the same space as text; supports text-as-query → figure hits and image-as-query
  • Question answering — — RAG capability with citations (page numbers, section headings)
  • Vision QA — — Vision-capable models receive figure bytes alongside chunk text; attach your own images to questions in ask, analyze, MCP, and the chat TUI
  • Reranking — — local cross-encoders, Cohere, Zero Entropy, or vLLM
  • Analysis capability — — Complex analytical tasks via sandboxed Python code execution (aggregation, computation, multi-document analysis)

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at haiku.rag on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by ggozad; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the haiku mcp server does with a few real requests.

How to install the Haiku MCP server

{
  "mcpServers": {
    "haiku-rag": {
      "command": "uvx",
      "args": ["haiku.rag"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Frequently asked questions

It connects Haiku to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Haiku directly.