Voyageai Cli

@mrlynn

Visit Server

4 months ago

MCP server for Voyage AI embeddings, reranking, and MongoDB Atlas Vector Search. Provides 11 tools for semantic search, document ingestion, cost estimation, and model exploration. Full RAG pipeline: chunk, embed, vector search, and rerank from any MCP client.

Overview Tools Comments

Overview

What is voyageai-cli?

An MCP server that gives AI agents access to Voyage AI's embedding and reranking models plus MongoDB Atlas Vector Search. Build RAG pipelines without leaving your agent.

11 Tools

Retrieval: vai_query (full RAG), vai_search (vector search), vai_rerank (reranking)

Embedding: vai_embed (generate vectors), vai_similarity (cosine similarity)

Management: vai_collections (list indexes), vai_models (browse models)

Utility: vai_topics, vai_explain (learn about embeddings/RAG), vai_estimate (cost calculator)

Ingestion: vai_ingest (chunk, embed, store documents)

Install

npm install -g voyageai-cli vai mcp install claude-code vai mcp install all

Or use npx with no install required (see Server Config above).

Requirements

Node.js 20+
Voyage AI API key (free at dash.voyageai.com)
MongoDB Atlas cluster (for retrieval/ingestion tools, optional for utility tools)

Server Config

{
  "mcpServers": {
    "vai": {
      "command": "npx",
      "args": [
        "voyageai-cli",
        "mcp-server"
      ],
      "env": {
        "VOYAGE_API_KEY": "<YOUR_VOYAGE_API_KEY>"
      }
    }
  }
}

Build with ShipAny.