How to Use the Redis Vector MCP in Windsurf

Q: Can I create new indexes using Redis Vector inside Windsurf?

Yes, Cascade invokes createvectorindex with your specified dimensions. It plans the execution, sets up the RediSearch index, and verifies it works.

Q: Does the Redis Vector integration require manual schema configuration in Windsurf?

No, the agent handles schema discovery itself. It calls listindexes and getindexinfo to understand your database layout before writing any code.

Let Windsurf Cascade autonomously run KNN similarity searches and manage your vector indexes.

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 Windsurf

Create your Vinkius account to connect Redis Vector to Windsurf — 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build vector indexes directly from Cascade

The `create_vector_index` tool sets up a new RediSearch index with your specified dimensions directly inside your workspace. Cascade takes your index configuration and runs the setup without requiring manual CLI commands. You can let Cascade check existing setups with `list_indexes` to avoid duplicates. It handles the index creation step as part of a larger coding workflow, immediately preparing your database for incoming embeddings.

Autonomous similarity search during code generation

The `search_vectors` tool queries your Redis database using a JSON array of floats to find nearest neighbors. When you ask Cascade to fix a recommendation bug, it extracts the target vector, runs the KNN search, and analyzes the raw results. Cascade uses this data to write or debug your query logic. It reads the returned document keys and updates your application code based on actual database responses.

Continuous index management via this MCP Server

The `upsert_vector` tool writes or updates your embeddings in a Redis hash as your application state changes. Cascade hooks into your local test runs to populate the index with sample vectors. If a test fails or data changes, Cascade runs `delete_vector` to clean up the stale records. It monitors index health using `get_index_info` to ensure your dimensions match your embedding model.

Setup guide

Set up Redis Vector MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Redis Vector 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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Redis Vector payment history." If connected, Cascade will call the Redis Vector tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade converts your raw queries into float arrays and passes them to `search_vectors`. It executes this process autonomously when you ask it to debug or build search features.

Yes, Cascade invokes `create_vector_index` with your specified dimensions. It plans the execution, sets up the RediSearch index, and verifies it works.

No, the agent handles schema discovery itself. It calls `list_indexes` and `get_index_info` to understand your database layout before writing any code.

Open your Windsurf settings and add the server configuration under the MCP configuration key. Once you hit refresh, Cascade instantly detects the six vector tools.

Your vector float arrays and document keys never leave your local environment or secure Vinkius sandbox. This MCP Server processes all database operations within an isolated V8 sandbox, preventing external exposure of your raw embeddings.

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