How to Use the Weaviate MCP in Claude

Q: How do I check the operational status of the Weaviate cluster with Claude Desktop?

You call getclusternodes on the MCP Server. This tool pulls live data about every node running in your Weaviate environment, so you know if the entire cluster is up and stable.

Q: Can I see all available collections when setting up a new workflow with Claude Desktop?

Yep. Call getfullschema. It retrieves the complete schema definition for every collection in your Weaviate instance, giving you a full inventory of what data is stored.

Q: If I'm debugging a query, how can I get metadata about the Weaviate instance using Claude Desktop?

Just run getinstancemetadata. This tells your agent everything it needs to know about the specific Weaviate deployment you’re connected to. It's useful for verifying environment variables and setup.

Connect Weaviate's vector database directly within Claude Desktop for local development.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weaviate MCP to Claude Desktop

Create your Vinkius account to connect Weaviate to Claude Desktop 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 Weaviate with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage the MCP Server schema using Claude Desktop

Use `get_full_schema` to pull the entire structure of your Weaviate instance. This gives you a map of every class (collection) available, letting you know exactly what data types exist. You can also call `get_class_schema` if you only care about one specific collection. Knowing these schemas up front lets your agent write precise queries against the MCP Server.

Perform deep similarity searches with Weaviate

The core function is `search_near_vector`. You provide a class name and a vector (a JSON array of floats), and the server returns the nearest neighbors. It’s how you build production-grade AI apps that actually find relevant context. This tool bypasses simple keyword searches, letting your agent understand semantic meaning between queries and stored data.

Get specific object details or list records

Need to check a single record? `get_object_details` takes a UUID and spits out the full metadata. Alternatively, `list_objects` lets you paginate through all entries in a class, limited by count. These basic listing tools keep your agent grounded when it needs to inspect existing data before running complex searches.

Setup guide

Set up Weaviate 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 Weaviate 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 Weaviate 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 weaviate-mcp.

json

{
  "mcpServers": {
    "weaviate-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 Weaviate. 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 Weaviate 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 Weaviate MCP in Claude Desktop

You call `get_cluster_nodes` on the MCP Server. This tool pulls live data about every node running in your Weaviate environment, so you know if the entire cluster is up and stable.

Yep. Call `get_full_schema`. It retrieves the complete schema definition for every collection in your Weaviate instance, giving you a full inventory of what data is stored.

Just run `get_instance_metadata`. This tells your agent everything it needs to know about the specific Weaviate deployment you’re connected to. It's useful for verifying environment variables and setup.

The server works with structured data objects, indexed by their UUID. The tools allow you to list these records within specific classes defined in the Weaviate schema.

You must supply a class name and your query vector as a JSON array of floats. The `search_near_vector` tool requires both pieces of information to execute the nearest neighbor search.

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