How to Use the Weaviate MCP in Windsurf

Q: How do I perform vector searches with Weaviate using Windsurf?

You call searchnearvector by specifying the target class name and passing your query as a JSON array of floats. Cascade executes this step, returning relevant object UUIDs and their metadata for you to work with.

Q: What kind of operational data can I get from Weaviate using Windsurf?

You'll find tools to check the cluster health by running getclusternodes. This shows exactly which nodes are up and what their current status is, helping you debug deployment issues.

Q: Can I get a full map of all data types using Weaviate and Windsurf?

Absolutely. Calling getfullschema gives you a complete overview of every single collection in your instance. This is the quickest way to understand the entire database structure.

Q: Does this MCP Server support basic data listing for Windsurf?

Yes, the listobjects tool supports pagination via a limit parameter. You can pull batches of records from any specified class name when you need to iterate over a dataset.

Execute multi-step vector searches and data schema checks directly inside your IDE using Windsurf.

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 Windsurf

Create your Vinkius account to connect Weaviate to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector Similarity Search with Windsurf

You can run nearest neighbor lookups across any collection by providing a class name and the query vector via `search_near_vector`. Cascade handles formatting that JSON array of floats, so you just set the goal. It returns the most similar data objects based on their embeddings.

Inspect Full Schema using Windsurf MCP Server

Need to know what fields exist before writing a query? Use `get_full_schema` to map out every collection in your Weaviate instance. You can then drill down further by calling `get_class_schema` if you only care about one specific dataset.

Fetch Object Details using Windsurf

If you get a UUID, you don't have to list everything just to check something. Use `get_object_details` to pull the complete metadata for any record instantly. This keeps your agent focused and efficient.

Setup guide

Set up Weaviate 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 Weaviate 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 Weaviate payment history." If connected, Cascade will call the Weaviate tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You call `search_near_vector` by specifying the target class name and passing your query as a JSON array of floats. Cascade executes this step, returning relevant object UUIDs and their metadata for you to work with.

You'll find tools to check the cluster health by running `get_cluster_nodes`. This shows exactly which nodes are up and what their current status is, helping you debug deployment issues.

Absolutely. Calling `get_full_schema` gives you a complete overview of every single collection in your instance. This is the quickest way to understand the entire database structure.

Yes, the `list_objects` tool supports pagination via a limit parameter. You can pull batches of records from any specified class name when you need to iterate over a dataset.

The server primarily works with schema definitions and object UUIDs. The `get_instance_metadata` tool provides general information about the entire database setup, not specific user data.

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