Setup & Installation
npx skills add https://github.com/mongodb/agent-skills --skill mongodb-search-and-ai
https://github.com/mongodb/agent-skills/tree/main/skills/mongodb-search-and-ai
View on GitHubWhat This Skill Does
Helps MongoDB users pick between Atlas Search, Vector Search, and Hybrid Search, then build the indexes and aggregation pipelines to match. Covers schema inspection, version checks for $rankFusion/$scoreFusion, and query refinement through the MongoDB MCP server.
Routes you to the correct search type and index shape based on your actual schema and cluster version, instead of guessing between $regex, $text, Atlas Search, and Vector Search on your own.
When to use it
- Adding typo-tolerant autocomplete to a product catalog with fuzzy matching
- Building a RAG pipeline that retrieves document chunks by embedding similarity
- Combining keyword filters with semantic ranking for a movie recommendation query
- Replacing a slow $regex 'contains' query with an Atlas Search text operator
- Creating a faceted search over listings with price, category, and date filters