How to Use the Typesense Vector Search MCP in Claude Code

Q: How do I perform a Typesense Vector Search using Claude Code?

You run searchvectors from your terminal script. You pipe the collection name, text query, and vector string as arguments. It's designed for non-interactive execution.

Q: Can I manage document schemas with Typesense Vector Search using Claude Code?

Yes. Use createcollection to define the schema details in a JSON object within your script. This makes setting up new search indexes part of your infrastructure automation.

Q: What is the best way to run Typesense Vector Search in CI/CD with Claude Code?

You should call searchvectors at the end of your deployment job. This validates that the index is fully populated and searchable using a predefined test query.

Q: Does this server allow me to remove data?

Yeah, you use deletedocument. Just remember it's irreversible. It removes a document by its ID, so make sure your script logic is sound before running it.

Automate complex indexing and semantic searches in headless CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typesense Vector Search MCP to Claude Code

Create your Vinkius account to connect Typesense 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 Typesense Vector Search with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision search collections from the terminal

Start by listing all available indexes using `list_vector_collections` to confirm scope. Then, execute `create_collection`, providing the necessary schema JSON object directly in your script. This is perfect for CI/CD setup scripts that need to ensure the search environment exists before deploying code.

Batch index documents via CLI

Use `index_document` within a shell loop or cron job. This tool takes your collection name and document data (JSON format) and pushes it to Typesense. It's reliable for background syncing. You can build pipelines that process raw data feeds and index them immediately, making the search results live.

Perform programmatic vector similarity searches

Run `search_vectors` from a script by passing the collection name, text query, and vector string. This allows you to test semantic relevance in a headless environment. It's ideal for post-deployment validation—you can check if your search functionality is working correctly before promoting the code.

Setup guide

Set up Typesense 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 typesense-vector-search-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http typesense-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 Typesense 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": {
    "typesense-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 Typesense 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 Typesense 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 Typesense Vector Search MCP in Claude Code

You run `search_vectors` from your terminal script. You pipe the collection name, text query, and vector string as arguments. It's designed for non-interactive execution.

Yes. Use `create_collection` to define the schema details in a JSON object within your script. This makes setting up new search indexes part of your infrastructure automation.

You should call `search_vectors` at the end of your deployment job. This validates that the index is fully populated and searchable using a predefined test query.

Yeah, you use `delete_document`. Just remember it's irreversible. It removes a document by its ID, so make sure your script logic is sound before running it.

This MCP Server handles structured JSON objects and vector embeddings—the core search index components. The actual document data is always stored in the collections you manage.

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