Skip to content
appsgit

haiku.rag

haiku.rag is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval. It has 622 GitHub stars, is released under the MIT license and runs locally with uvx haiku-rag.

github.com/ggozad/haiku.rag (opens in a new tab)

View on GitHub (opens in a new tab)Website (opens in a new tab)

Install haiku.rag

Generated from the server's MCP registry entry. Replace your-value with your own values.

Claude Desktop

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

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

Claude Code

claude mcp add --transport stdio haiku-rag -- uvx haiku-rag

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "haiku-rag": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "haiku-rag"
      ]
    }
  }
}

Project file; use ~/.cursor/mcp.json to enable it in every project.

VS Code

.vscode/mcp.json
{
  "servers": {
    "haiku-rag": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "haiku-rag"
      ]
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

About haiku.rag

Agentic RAG that answers questions about your own documents with citations to page numbers and section headings. It runs on an embedded LanceDB database with open models through Ollama by default, so no server or API key is needed. Any provider Pydantic AI supports works in their place, and the same database can live on S3, GCS, Azure or LanceDB Cloud.

  • mcp-server
  • rag
  • lancedb
  • pydantic-ai
  • docling
  • ag-ui
  • agentic-rag
  • code-execution
  • code-mode
  • cross-encoder

Similar MCP servers

More ai & search MCP servers

All AI & search

FAQ

haiku.rag FAQ

Still curious? Email info@appsgit.com.

What is haiku.rag?

haiku.rag is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval. It has 622 GitHub stars, is released under the MIT license and runs locally with uvx haiku-rag. The source code is at github.com/ggozad/haiku.rag.

How do I install the haiku.rag MCP server?

Add the command uvx haiku-rag to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.

Is haiku.rag free?

The server is open source under the MIT license, so running it is free. It does not declare any required API key.

Is haiku.rag actively maintained?

The most recent commit was on Oct 6, 2026. The latest release is 0.93.0, published Oct 6, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.