# Atlas Vector Search Docs

> Use this tool when you need to efficiently search and retrieve technical documents based on semantic meaning, or generate text using relevant document context. It solves problems of information overload and poor search results by leveraging AI-powered vector search and embeddings. The tool takes in markdown documents and outputs relevant search results, supporting integration with AI assistants for augmented generation workflows.

Canonical page: https://skillsregistry.net/skills/atlas-vector-search-docs  
JSON: https://api.skillsregistry.net/v1/skills/atlas-vector-search-docs

## Description

A vector search system for document retrieval using MongoDB Atlas Vector Search and Voyage AI embeddings, created by Pat Wendorf from MongoDB. The implementation ingests and chunks markdown documents with hierarchical headers, generates contextual embeddings using Voyage AI's API, and stores documents with embeddings in MongoDB collections with parent-child relationships. Built with FastMCP for integration with AI assistants like Claude Desktop, it enables semantic search across technical documentation and supports configurable vector dimensions, automatic quantization, and pre-filtering capabilities for efficient document discovery and retrieval-augmented generation workflows.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/atlas-vector-search-docs)
- **Repository:** <https://github.com/patw/avs-docs-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "atlas-vector-search-docs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/atlas-vector-search-docs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/atlas-vector-search-docs/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt