How to Use the Redis Vector MCP in Cursor

Q: How do I add the Redis Vector MCP Server to my Cursor editor?

Create a .cursor/mcp.json file in your project root and add the server under the mcpServers key. The Cursor agent will immediately gain access to the vector tools.

Q: How does the Cursor MCP Server handle index creation with Redis Vector?

The agent uses createvectorindex to define the index name and vector dimensions. You just specify the parameters in the chat, and Cursor handles the JSON payload.

Generate code that queries Redis Vector indexes and run live KNN searches directly in Cursor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Redis Vector MCP to Cursor

Create your Vinkius account to connect Redis Vector to Cursor — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Redis Vector with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute live KNN searches while writing code in Cursor.

The `search_vectors` tool allows the Cursor agent to run real-time K-nearest neighbor searches directly against your active Redis database. As you write code in the Cursor editor, your agent pulls actual float arrays and similarity scores instead of relying on mock data. This integration changes how you debug vector search pipelines directly inside Cursor. You can ask the Cursor composer to check your query results, and it will call this MCP Server to fetch real Redis matches right into your workspace.

Manage RediSearch schemas inside your code editor.

The `create_vector_index` tool lets the Cursor agent spin up new RediSearch indexes by defining vector dimensions and distance algorithms directly from your editor prompt. You can bootstrap a new 1536-dimension index for your project without leaving your active Cursor workspace. To check your setup, the Cursor agent uses `list_indexes` and `get_index_info` to inspect the structural details of your Redis hashes. This live feedback ensures your Cursor workspace matches your active vector database schema.

Upsert and delete vectors during your Cursor debug sessions.

The `upsert_vector` tool writes your float arrays and document keys directly to Redis hashes from your Cursor composer window. If you are testing an embedding generator, Cursor can write test vectors to your database instantly. When you need to clean up your development database, the Cursor agent calls `delete_vector` to purge specific keys. You maintain a clean Redis environment without switching away from your Cursor coding session.

Setup guide

Set up Redis Vector MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Redis Vector MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Redis Vector transactions." If the MCP tools are loaded correctly, Cursor will call the Redis Vector tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "redis-vector-mcp": {
      "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 Redis Vector. 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 Redis Vector 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 Redis Vector MCP in Cursor

Create a `.cursor/mcp.json` file in your project root and add the server under the `mcpServers` key. The Cursor agent will immediately gain access to the vector tools.

Yes, when you ask Cursor to find similar documents, it calls `search_vectors` with your query float array. The results are injected directly into your active composer window.

No, this server handles the connection details. Cursor calls the tools directly, allowing you to manage indexes and search vectors using natural language.

The agent uses `create_vector_index` to define the index name and vector dimensions. You just specify the parameters in the chat, and Cursor handles the JSON payload.

Your document keys and float arrays are sent directly to your configured Redis instance. Cursor uses the MCP protocol to communicate safely with your database, keeping your database credentials secure.

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