MongoDB Atlas Vector Search Connector for AI agents.
6 live capabilities
Query embeddings and manage Atlas data with natural language.
Waiting for input…
Why people use MongoDB Atlas Vector Search
Stop the Manual Grind of Vector Indexing with MongoDB Atlas Vector Search
With this Connector, that friction disappears. You can stay inside your IDE or chat interface and simply tell your agent to create a new index or find a specific record. It turns a multi-step configuration task into a single sentence. You get immediate confirmation and a clear view of your data without ever leaving your workspace.
What Vinkius changes
You get a direct line to your Atlas data without writing a single line of boilerplate code.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Testing vector relevance
An ML engineer asks the agent to find the top 5 matches for a new product embedding and checks the similarity scores using search.
- Real-world use case 02
Production data auditing
A backend developer asks the agent to list all collections and find users with a 'pro' status to verify a recent migration.
- Real-world use case 03
Rapid index prototyping
A search architect uses create_index to test different dimension mappings for a new content category without opening the Atlas UI.
Complete set · 6capabilities
The complete MongoDB Atlas Vector Search capability set.
These are the exact actions your AI can choose when you ask it to work with MongoDB Atlas Vector Search.
01—03
3 capabilities in this set.
Part of 6 available through MongoDB Atlas Vector Search.
- 01 Capability
Search
Run high-dimensional similarity searches using $vectorSearch. It finds the most relevant matches based on your raw embedding vectors.
- 02 Capability
Find
Locate standard MongoDB documents using MQL filters. This helps you grab specific data points without using vector logic.
- 03 Capability
Insert
Add new JSON records into your target collections. Use this to keep your data fresh and ready for search.
04—06
3 capabilities in this set.
Part of 6 available through MongoDB Atlas Vector Search.
- 04 Capability
Delete
Remove specific documents from your database. You can target records based on the filters you provide in the chat.
- 05 Capability
List collections
See all the data collections in your Atlas environment. This helps you understand your database organization quickly.
- 06 Capability
Create index
Build new search indices with custom dimensions. This lets you configure how your cluster handles similarity calculations.
Set up in minutes
One URL. Then ask MongoDB Atlas Vector Search to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use MongoDB Atlas Vector Search from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it MongoDB Atlas Vector Search, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable MongoDB Atlas Vector Search for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the MongoDB Atlas Vector Search URL.
- Step 03
Save and start
Save the connection and enable MongoDB Atlas Vector Search in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"mongodb-atlas-vector-search": {
"url": "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using MongoDB Atlas Vector Search
Open Agent mode in chat and ask: "Using MongoDB Atlas Vector Search, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"mongodb-atlas-vector-search": {
"url": "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using MongoDB Atlas Vector Search
Ask Copilot: "Using MongoDB Atlas Vector Search, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"mongodb-atlas-vector-search": {
"url": "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using MongoDB Atlas Vector Search
Open Cascade and ask: "Using MongoDB Atlas Vector Search, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"mongodb-atlas-vector-search": {
"url": "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using MongoDB Atlas Vector Search
Ask Cline: "Using MongoDB Atlas Vector Search, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add mongodb-atlas-vector-search --transport http "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using MongoDB Atlas Vector Search
Ask Claude: "Using MongoDB Atlas Vector Search, show me...". 6 tools are ready
Where the request belongs
Work MongoDB Atlas Vector Search can move forward.
This is for the engineers who are tired of context-switching between their database console and their code editor. It targets those building production-grade vector search systems who need to iterate quickly on embeddings and data structure.
ML Engineer
Tests vector relevance and verifies embedding dimensions through chat instead of writing manual SDK scripts.
Backend Developer
Manages production data and vector results in a single workflow directly from their workspace terminal.
Search Architect
Audits search indices and monitors collection organization across multiple Atlas environments efficiently.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsCouchbase (Vector & NoSQL)
Manage vector search and NoSQL via Couchbase. execute N1QL queries, perform KNN vector searches, and audit documents directly from any AI agent.
Milvus (Open-Source Vector Database)
Manage vector storage via Milvus. perform ANN searches, query scalar entities, and audit collections.
MyScale (SQL Vector Database API)
Manage MyScale vector databases via SQL. execute queries, perform vector searches, and manage indices directly from any AI agent.
Zilliz Cloud
Manage vector collections and perform similarity searches via Zilliz Cloud.
Qdrant
Empower your AI to interact directly with your Qdrant vector database. query clusters, perform similarity searches, and manage collections effortlessly.
LanceDB (Serverless Vector DB)
Manage vectorized data via LanceDB. perform similarity searches, create tables, and manage multi-modal embeddings.
Bring your own AI
Change the model, client or framework. Keep MongoDB Atlas Vector Search connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about MongoDB Atlas Vector Search.
The practical details behind the request, access and result.
Can I use MongoDB Atlas Vector Search MCP to manage my standard NoSQL data too?
Yes. This Connector handles both your vector embeddings and your standard MongoDB documents. You can perform similarity searches and MQL queries in the same conversation.
How does MongoDB Atlas Vector Search MCP help with RAG workflows?
It makes it much easier to query your knowledge base. You can ask your agent to find relevant context using vector similarity without having to write the $vectorSearch queries yourself.
Do I need to write any code to use MongoDB Atlas Vector Search MCP?
No. Once you've connected your API keys, you can manage your indices, find records, and run searches using plain English instructions to your agent.
Can the MongoDB Atlas Vector Search MCP create new indices for me?
Yes. You can describe the dimensions and mappings you need, and the Connector will provision the Atlas Search index for you automatically.
Is MongoDB Atlas Vector Search MCP safe for production data?
It uses your existing Atlas Data API credentials. It performs the same operations as your authorized scripts, just through a conversational interface.
What happens if I want to delete a specific record using the Connector?
You just tell your agent which record to remove based on its attributes. The Connector will then use the appropriate filters to delete that document for you.
Can I manage both vector search and standard data in the same conversation?
Yes. MongoDB Atlas Vector Search is unified. You can use the search capability for similarity and the find or insert capabilities for standard operational data management using MQL, allowing you to bridge both worlds natively.
How do I create a new vector search index through the agent?
Use the create_index capability by providing the database, collection, and required dimensions (matching your embedding model). Your agent will provision the index infrastructure on Atlas to enable high-speed vector retrieval.
Can my agent find specific documents using standard MongoDB query filters?
Absolutely. Use the find capability with a JSON string representing your MQL filter (e.g. {"status":"active"}). Your agent will execute the Data API request and return the matching documents and their scalar properties securely.
One connection away
Give your agent a direct line to MongoDB Atlas Vector Search.
Connect MongoDB Atlas Vector Search once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available