MongoDB Atlas Vector Search
https://www.mongodb.com/products/platform/atlas-vector-search
Agent memory store for both short-term (document) and long-term (vector). LangGraph checkpointer for stateful agents. Vector search extended to Community Edition (Sept 2025).
At a glance
- Type
- Vector embedded in document DB
- Tier
- T1
- Section
- Vector-database infrastructure
- Created
- 2016
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Pay-per-use
- Funding
- $311M VC pre-IPO; IPO 2017 NASDAQ:MDB; revenue $2.46B FY2026
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- overwrite
- unit
- document
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: low-latency similarity search + scale
Anti-fit: not for relational / graph-heavy queries (vector-first by design)
Pros & cons
Pros
Vector search inside the database your app already uses — eliminates a separate vector DB for many MongoDB-shop architectures.
Cons
Vector index quality lags dedicated engines on benchmark recall; pricing tied to Atlas tier.
Claims & capabilities
Converged document + vector store for agentic RAG.
Technical surface
- API surface
- MongoDB wire protocol, REST (Atlas Data API), SDK: many languages
- Backend storage
- MongoDB (with Lucene-based vector index)
- Deployment
- Managed-only
- Embedding model
- BYO
- Multi-tenancy
- Project/cluster/database isolation; dedicated cluster tier; PrivateLink; JWT-based tenant scoping for multi-tenant apps
- MCP
- via official adapter — MongoDB MCP server
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- first-class — Atlas + OTel
Similar systems
Other vector-database infrastructure in the catalog, ranked by inbound references.
- Qdrant T1
Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.
- pgvector T1
Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.
- Pinecone T1
Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .
- Chroma T1
Limited native hybrid (users build RRF custom). Fast Rust core (v2.5).
- LanceDB T1
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
- Milvus T1
Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).
Related systems
References (1)
- LangGraph Persistence integrates with — LangGraph checkpointer for stateful agents.
Referenced by (2)
- LangGraph Persistence builds on — Postgres / Mongo / Redis stores for production.
- n8n AI Agent Memory integrates with — vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall