How to Use the Redis Vector MCP in Claude

Q: How do I connect the Redis Vector MCP Server to my Claude Desktop app?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Once you save and restart the Claude Desktop app, you will see the hammer icon in your chat window indicating the vector tools are active.

Q: What embedding dimensions can I configure with Redis Vector in Claude Desktop?

You can specify any dimension size when running createvectorindex through the Claude Desktop chat. The agent handles the JSON array formatting for floats automatically.

Run KNN similarity searches and manage your Redis Vector indexes directly from your Claude Desktop chat.

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 Claude Desktop

Create your Vinkius account to connect Redis Vector to Claude Desktop — 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Redis Vector indexes directly inside Claude Desktop.

The `search_vectors` tool lets Claude Desktop execute K-nearest neighbor (KNN) similarity searches directly against your running Redis instance. When you paste raw text or ask a question in the chat, Claude converts your query into a float array to pull relevant document keys from your RediSearch index. You do not need to write custom Python scripts or open a separate terminal to query your Redis database from Claude Desktop. Instead, the desktop app calls this MCP Server via local stdio, pulling vector matches right into your active chat window so you can inspect raw float weights.

Build and inspect schemas without leaving the chat.

The `create_vector_index` tool lets your desktop agent configure new RediSearch schemas by specifying the exact index name and dimensions directly from your Claude Desktop prompt. This means you can spin up a new index for 1536-dimension OpenAI embeddings or 384-dimension local embeddings by just telling Claude what you need. If you need to check the configuration, Claude Desktop runs `get_index_info` or `list_indexes` to display the active vector fields and distance metrics. You see the exact layout of your Redis database directly in your Claude Desktop chat sidebar.

Edit and delete vector documents on the fly.

The `upsert_vector` tool writes your float arrays and document keys directly into Redis hashes through the Claude Desktop interface. When your desktop agent refines an embedding, it pushes the updated array immediately, keeping your Redis vector database in sync with your conversation. If a document becomes obsolete, telling Claude to purge it triggers `delete_vector` to wipe the hash from your Redis instance. This gives you absolute control over your Redis data store without leaving the Claude Desktop app.

Setup guide

Set up Redis Vector MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Redis Vector MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Redis Vector MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under redis-vector-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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Once you save and restart the Claude Desktop app, you will see the hammer icon in your chat window indicating the vector tools are active.

Yes. The desktop app communicates with this MCP Server via stdio, allowing Claude to execute `search_vectors` against local Redis instances running on localhost.

You can specify any dimension size when running `create_vector_index` through the Claude Desktop chat. The agent handles the JSON array formatting for floats automatically.

Yes, this server requires your Redis instance to have RediSearch enabled. Without it, tools like `list_indexes` will return errors in the desktop chat.

Your raw vector float arrays and document keys stay local to your machine during stdio execution. The MCP Server processes these vectors locally, meaning your sensitive coordinates are never sent to external servers.

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