Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
registry version 0.110.0
Python
uvx haiku-ragPython
uvx haiku-rag@0.110.0
Pick your client — the config below is generated for this server (local stdio). Copy respects the “Pin version” switch above.
claude_desktop_config.json
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag@0.110.0"
]
}
}
}Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add haiku-rag -- uvx haiku-rag
claude mcp add haiku-rag -- uvx haiku-rag@0.110.0
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag@0.110.0"
]
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}{
"servers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag@0.110.0"
]
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag@0.110.0"
]
}
}
}Format verified against the official Windsurf docs ↗.
⭐ 628 stars · 最近更新于 29 天前 · MIT license
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, an…
Summary from the project README — github.com/ggozad/haiku.rag
Distributed as Python, listed under Knowledge & Memory. Review our MCP security guide before granting access to real data.
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, an
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/ggozad/haiku.rag. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/haiku-rag/)
HTML
<a href="https://mcpnav.net/server/haiku-rag/"><img src="https://mcpnav.net/badge/haiku-rag.svg" alt="Listed on MCPNav" height="20"></a>