mcp server

raglite

TypeScript RAG toolkit for semantic search, multi-provider LLM Q&A, and document APIs.

creatorpiyush/raglitecommunitylistedunreviewed

Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

Node.js 20 or newer

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "creatorpiyush-raglite": {
      "command": "npx",
      "args": [
        "-y",
        "raglite-toolkit"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 14, 2026

raglite-toolkit

Semantic search, cited answers, an MCP server and agent tools over your documents, in a few lines of TypeScript.

Documentation · Getting started · Providers · MCP server · Troubleshooting · Changelog

RAGLite indexes PDFs, Word files, Markdown, text, JSON, folders and web pages, then searches them and answers questions with any LLM, citing the passages it used.

Answers with citations, including the PDF page and Markdown section of each passage
Hybrid search: vector search for meaning, BM25 for exact terms such as error codes, or both
Metadata filters and reranking, and raglite eval to measure retrieval on your own questions
MCP server for Claude Code, Claude Desktop, Cursor and VS Code, and an AI SDK tool for your own agents
Any provider: OpenAI, Anthropic, Google, Mistral, Cohere, Groq, xAI and Ollama; install only what you use
Fully local option: local embeddings and Ollama, no API key
Content-hash caching, Qdrant, Pinecone and LanceDB stores, streaming, a REST API and a CLI

Install

Requires Node.js 20 or later.

npm install raglite-toolkit
npm install @huggingface/transformers   # local embeddings (the default), no API key
npm install @ai-sdk/anthropic           # Claude answers; see Providers for the others

Quick start

import { Document } from "raglite-toolkit";

const doc = new Document("./policy.pdf", {
  llm: { provider: "anthropic", apiKey: process.env.ANTHROPIC_API_KEY },
});

await doc.build();

const hits = await doc.search("refund policy", { topK: 3 });

const answer = await doc.ask("What is the refund policy?");
console.log(answer.text); // "Refunds are issued within 30 days [1]."
console.log(answer.citations); // [{ n: 1, source: "policy.pdf", page: 12, text: "..." }]

Learn more

Collections: index folders, files and URLs together
Citations: pages and sections for each cited passage
Hybrid search: vector, keyword and hybrid retrieval
Metadata filters: search one customer's documents or a range of pages
Reranking: Cohere, Voyage, an LLM or your own function
Evaluating retrieval: raglite eval scores recall@k, MRR and hit rate on your questions
MCP server: give your documents to AI coding tools
Agent tools: asTool() for the Vercel AI SDK
Streaming, progress and cancellation
Vector stores: Qdrant, Pinecone, LanceDB or your own
REST API and CLI
How caching works
Options and types

Python

The same library for Python: raglite-toolkit on PyPI (source). Every page of the documentation has TypeScript and Python tabs.

Contributing

See CONTRIBUTING.md. Security issues: SECURITY.md.

License

MIT