Skip to content
Back to skills

Run Local Document Rag With Citations Over Mcp Using Haiku Rag

ASecurity

Index local or self-hosted documents, search them with hybrid and multimodal retrieval, and answer agent questions through an MCP server with citations.

  • 36 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentspythongogitsecuritydocumentation

Works with

  • cli
  • mcp

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned September 2, 2026

npx -y skills add agentskillexchange/skills --skill run-local-document-rag-with-citations-over-mcp-using-haiku-rag --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run Local Document Rag With Citations Over Mcp Using Haiku Rag?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Run Local Document Rag With Citations Over Mcp Using Haiku Rag
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-run-local-document-rag-with-citations-over-mcp-usi/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-run-local-document-rag-with-citations-over-mcp-usi)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "Run local document RAG with citations over MCP using Haiku.RAG"
slug: "run-local-document-rag-with-citations-over-mcp-using-haiku-rag"
description: "Index local or self-hosted documents, search them with hybrid and multimodal retrieval, and answer agent questions through an MCP server with citations."
github_stars: 581
verification: "security_reviewed"
source: "https://github.com/ggozad/haiku.rag"
author: "Yiorgis Gozadinos"
publisher_type: "individual"
category: "Data Extraction & Transformation"
framework: "MCP"
tool_ecosystem:
  github_repo: "ggozad/haiku.rag"
  github_stars: 581
---

# Run local document RAG with citations over MCP using Haiku.RAG

Index local or self-hosted documents, search them with hybrid and multimodal retrieval, and answer agent questions through an MCP server with citations.

## Prerequisites

Python 3.12+, haiku.rag or haiku.rag-slim, an embedding provider such as Ollama/OpenAI/VoyageAI/Cohere/LM Studio/vLLM, and an MCP-compatible client

## Installation

Install or set up from the source-backed instructions:

Install with `pip install haiku.rag` or `uv pip install haiku.rag`, index documents with commands such as `haiku-rag add-src paper.pdf`, then expose the knowledge base to an MCP client with `haiku-rag mcp --stdio`. Use `haiku-rag --read-only mcp --stdio` when the agent should only search and ask questions.

- Source: https://github.com/ggozad/haiku.rag

## Documentation

- https://ggozad.github.io/haiku.rag/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-local-document-rag-with-citations-over-mcp-using-haiku-rag/)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…