haiku.rag runs on your own machine — the client starts it, so there is no endpoint to ping. 4 287 installs a week from pypi. Last commit 30 Oct 2026.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
done = subprocess.run(
$("stat-breakdown").innerHTML = parts.join("<br>");
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add haiku-rag -- uvx haiku-rag{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}[mcp_servers.haiku-rag]
command = "uvx"
args = ["haiku-rag"]{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}{
"servers": {
"haiku-rag": {
"type": "stdio",
"command": "uvx",
"args": [
"haiku-rag"
]
}
}
}Alternatives to haiku.rag
same job, measured the same wayLocal-first RAG MCP server: hybrid search over a folder of your own documents
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Local-first RAG engine with MCP server for AI agent integration.
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
haiku.rag — questions
Answers built from our own checks of this server.