How to Use the MongoDB Atlas Vector Search MCP in Claude Code

Claude Code brings vector search to the terminal, letting you run headless database operations via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MongoDB Atlas Vector Search MCP to Claude Code

Create your Vinkius account to connect MongoDB Atlas Vector Search to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup MongoDB Atlas Vector Search with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless search for Claude Code

Claude Code executes `search` operations directly from your terminal session. It parses your vector query and outputs the results as JSON for your scripts to process. This is ideal for CI/CD pipelines where you need to verify embedding performance. You pipe the output into your validation scripts to ensure your model output matches your database records.

CLI-based indexing with Claude Code

Claude Code triggers `create_index` during your deployment or setup scripts. It ensures your vector fields are indexed correctly before your application starts its workload. This MCP Server provides the raw control needed for terminal-based infrastructure management. You automate the index lifecycle without needing a GUI or browser.

Manage records in Claude Code

Claude Code uses `find` and `insert` to manage data records directly from the shell. It treats your database as another local resource to be queried or updated. This workflow is built for DevOps engineers who need to patch data or check states in production. You get direct access to your collections through standard terminal commands.

Setup guide

Set up MongoDB Atlas Vector Search MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see mongodb-atlas-vector-search-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest MongoDB Atlas Vector Search transactions." It will automatically discover and invoke the available MongoDB Atlas Vector Search tools.

Terminal

claude mcp add --transport http mongodb-atlas-vector-search-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the MongoDB Atlas Vector Search MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "mongodb-atlas-vector-search-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MongoDB Atlas Vector Search. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MongoDB Atlas Vector Search now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about MongoDB Atlas Vector Search MCP in Claude Code

Yes. You can invoke the search tool within your shell scripts or CI pipelines. It returns the data directly to stdout for further processing.

The server supports HTTP and stdio transports. You configure the connection string in your local config, and Claude Code handles the rest.

The tool output is plain JSON. You can pipe it into tools like jq to filter or verify specific fields immediately after the search runs.

It does. You can pass your document data to the insert tool, and it handles the write operation in your cluster.

The server uses your endpoint token to authenticate. All data transit is encrypted, and Claude Code only accesses the specific collections defined in your scope.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript