An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect MongoDB Atlas Vector Search to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage vector embeddings and operational data through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through MongoDB Atlas Vector Search.

  1. 01

    Search

    This capability runs $vectorSearch queries to find highly-dimensional matches in your collections.

  2. 02

    Create index

    Use this to build standard embedding search indices with specific dimension constraints.

  3. 03

    Delete

    This capability removes documents from your collections based on parsed MongoDB filters.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through MongoDB Atlas Vector Search.

  1. 04

    Find

    This capability retrieves standard MongoDB documents by resolving your specific query filters.

  2. 05

    Insert

    Use this to add new, distinct JSON documents into your target collections.

  3. 06

    List collections

    This capability returns a list of all data collections available within your Atlas limits.

Real work

What teams actually run

01

Embedding Validation

Test how well your vectors retrieve relevant documents by running similarity searches through your agent.

02

Database Auditing

Check collection organization and schema boundaries across multiple Atlas environments.

03

Data Maintenance

Clean up or update records using MQL filters directly from your AI client.

04

Index Optimization

Create and adjust search indices to improve how your cluster handles similarity calculations.

Automate a task

Put MongoDB Atlas Vector Search to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

MongoDB Atlas Vector Search works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put MongoDB Atlas Vector Search to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

910ms average. Fast in production.

MongoDB Atlas Vector Search is checked daily against the live service.

Daily averagePeak 1215ms
Oct 8Today
Fastest day
750ms
Slowest day
1215ms
14-day trend
Improving-12%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of MongoDB Atlas Vector Search, so you can see the experience inside your AI.

It does not authenticate your account with MongoDB Atlas Vector Search. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

MongoDB Atlas Vector Search Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — MongoDB Atlas Vector Search capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "mongodb-atlas-vector-search-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_rMRfujNKzotBfoPOFvzesaIZTdVkigbmunZrRwce/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up MongoDB Atlas Vector Search in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work MongoDB Atlas Vector Search owners hand off.

This MCP is built for engineers who need to bridge the gap between vector embeddings and operational database management.

  • 01

    ML Engineers

    They use the agent to test vector relevance and verify embedding dimensions without writing SDK scripts.

  • 02

    Backend Developers

    They manage operational data and vector search results within their existing workspace.

  • 03

    Search Architects

    They audit search indices and monitor collection organization across different Atlas environments.

FAQ

Questions MongoDB Atlas Vector Search owners ask.

  • 01

    What AI clients can I use with this MCP?

    You can connect this MCP to any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 02

    Do I need to write MQL manually?

    No. You can describe the data you want to find or change in plain language, and your agent will handle the MQL execution.

  • 03

    Can I manage my search indices?

    Yes. The MCP includes a capability to create and configure Atlas Search indices with custom dimensions.

  • 04

    Does this work with standard MongoDB documents?

    Yes. Beyond vector search, you can use standard MQL filters to find, insert, and delete documents.

  • 05

    Where is the data hosted?

    The data stays in your MongoDB Atlas cluster. Vinkius simply hosts the MCP that allows your agent to talk to your cluster.

  • 06

    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.

  • 07

    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.

  • 08

    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.

Explore

More in Industry Titans

Suggestions

Connect MongoDB Atlas Vector Search to Claude, Cursor, ChatGPT & more