MCP Server is a starter kit to build local-only AI apps that cost $0 to run, starting with document Q&A. It's written in Javascript and based on AI Starter Kit.

What technologies are used in MCP Server?

MCP Server uses Ollama for inference, Supabase pgvector for VectorDB, Langchain.js for LLM Orchestration, and Next.js for the app logic.

How do I get started with MCP Server?

Fork the repo, clone it, install dependencies, install Ollama, run Supabase locally, fill in secrets, generate embeddings, and then run the app locally.

Can I deploy MCP Server to the cloud?

Yes, you can follow instructions on AI Starter Kit for using Clerk, Pinecone/Supabase, OpenAI, Replicate, and other cloud-based vendors.

UBOS is a Full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.

What are the use cases for MCP Server?

Personal Knowledge Management, Internal Knowledge Base, Educational Tools, Research and Analysis, and Legal Document Review are among potential use cases.