How to Use the Redis Vector MCP in Claude Code

Q: Can I run similarity searches using Redis Vector directly in Claude Code?

Yes, you can pass float arrays to searchvectors through Claude Code. The terminal client runs the KNN search and prints the raw results directly to your standard output.

Q: How does Claude Code handle index creation in Redis Vector?

Claude Code invokes createvectorindex with your defined dimensions. It handles the entire creation process directly from your command-line interface.

Q: Is it possible to automate Redis Vector updates using Claude Code scripts?

Yes, you can use upsertvector in headless scripts to update your database. Claude Code executes these operations sequentially in your terminal session or deployment pipeline.

Q: How do I configure this MCP Server for my terminal environment?

Run the claude mcp add command with the transport flag and server URL. This saves the configuration to your local settings file for instant access.

Query and manage your Redis vector indexes directly from the Claude Code terminal.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Command-line index management with this MCP Server

The `list_indexes` tool lists all available RediSearch vector indexes directly in your terminal. Claude Code uses this to audit your database state without forcing you to open a Redis CLI session. This terminal-based discovery allows you to check active indexes during deployment scripts. Claude Code reads the output and pipes it to other CLI utilities if needed.

Automated vector cleanup in CI/CD pipelines

The `delete_vector` tool removes specific vector documents from your Redis instance. Claude Code runs this tool during automated cleanup jobs to purge test data or outdated embeddings. You can trigger this process via cron or terminal commands. Claude Code handles the deletion and verifies the document is gone by checking the index status.

Run similarity search from your Claude Code terminal

The `search_vectors` tool executes KNN similarity searches using raw JSON float arrays. Claude Code runs this tool when you need to quickly test search accuracy from your shell. The terminal client displays the nearest matches instantly. This lets you debug embedding models and distance metrics without writing custom Python testing scripts.

Setup guide

Set up Redis Vector 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 redis-vector-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http redis-vector-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 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

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": {
    "redis-vector-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 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 Code

Yes, you can pass float arrays to `search_vectors` through Claude Code. The terminal client runs the KNN search and prints the raw results directly to your standard output.

Claude Code invokes `create_vector_index` with your defined dimensions. It handles the entire creation process directly from your command-line interface.

Yes, you can use `upsert_vector` in headless scripts to update your database. Claude Code executes these operations sequentially in your terminal session or deployment pipeline.

Run the `claude mcp add` command with the transport flag and server URL. This saves the configuration to your local settings file for instant access.

This MCP Server processes raw float arrays and hash keys locally over encrypted transport. The Vinkius sandbox ensures your proprietary vector payloads never touch third-party intermediate 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