ndjordjevic/pinrag

Overview

pinrag is a Retrieval-Augmented Generation system built with LangChain, packaged as an MCP server for use with AI assistants like Cursor and VS Code. It enables these tools to query a custom knowledge base and retrieve relevant context to enhance responses.

Best for

Best for
Developers who want to integrate a custom RAG pipeline into Cursor or VS Code using MCP

Use cases

• Connecting a codebase or documentation to Cursor for context-aware code suggestions
• Providing VS Code with a document retrieval backend for Q&A on private knowledge
• Building a lightweight RAG pipeline that integrates with any MCP-compatible assistant

Notes

pinrag is a Retrieval-Augmented Generation system built with LangChain, packaged as an MCP server for use with AI assistants like Cursor and VS Code. It enables these tools to query a custom knowledge base and retrieve relevant context to enhance responses.

1 stars on GitHub. Last updated 2026-04-10. Licensed MIT.

Use cases

• Connecting a codebase or documentation to Cursor for context-aware code suggestions
• Providing VS Code with a document retrieval backend for Q&A on private knowledge
• Building a lightweight RAG pipeline that integrates with any MCP-compatible assistant

Pros

• Leverages LangChain for modular RAG pipeline construction
• Uses the MCP standard for broad compatibility with modern AI assistants
• Lightweight Python implementation easy to extend or customize

Cons

• Very early stage with only 1 star, indicating limited testing and community
• Requires manual setup of the MCP server and connection to an LLM endpoint
• No built-in vector store or embedding management; must be configured by the user

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.