How to Use the Anyscale MCP in Windsurf

Q: How does Windsurf use the Anyscale MCP Server to run batch jobs?

Windsurf calls listjobs to monitor active training pipelines. Cascade reads this state and updates your local workspace files automatically.

Q: Can I query Llama models on Anyscale directly from Windsurf?

Yes. Cascade uses the chatcompletion tool to send messages to your endpoints and displays the responses directly in your chat sidebar.

Q: How do I configure this Anyscale MCP Server in Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. You can also use the Cascade MCP Servers UI to paste the endpoint URL.

Q: What tools does this server provide for checking endpoint status?

It exposes listservices and getservice to check your active deployments. Your agent uses these to verify that your cluster is running before executing API calls.

Query Anyscale models and track cluster jobs directly inside your Windsurf workspace using Cascade.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anyscale MCP to Windsurf

Create your Vinkius account to connect Anyscale 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 Anyscale with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Llama queries inside Windsurf

The `chat_completion` tool sends conversational prompts directly to your hosted Llama models on Anyscale. Cascade uses this to test prompts and generate responses inline while you work on your application logic. You can also swap to the `text_completion` tool when you need raw, unstructured text generation for custom formatting tasks. This lets you run rapid evaluations against different model versions without leaving your file editor.

Automated batch job tracking with this MCP Server

The `list_jobs` tool pulls the status of your active training and batch processing runs on your cluster. Cascade watches these runs and notifies you the second a job finishes or fails, preventing wasted idle time. By combining this with the `list_models` tool, Cascade checks which fine-tuned weights are ready for deployment. Your agent then maps the new model IDs straight into your local configuration files.

Live service monitoring and vector generation

The `list_services` tool fetches the current operational state of your deployed Anyscale endpoints. Cascade checks this list to make sure your production endpoints are active before pushing code updates. When building search features, the `generate_embeddings` tool creates vector representations of your text inputs. Cascade runs this to test your indexing logic locally before you commit to database migrations.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "anyscale-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 Anyscale. 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 Anyscale 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 Anyscale MCP in Windsurf

Windsurf calls `list_jobs` to monitor active training pipelines. Cascade reads this state and updates your local workspace files automatically.

Yes. Cascade uses the `chat_completion` tool to send messages to your endpoints and displays the responses directly in your chat sidebar.

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the mcpServers key. You can also use the Cascade MCP Servers UI to paste the endpoint URL.

It exposes `list_services` and `get_service` to check your active deployments. Your agent uses these to verify that your cluster is running before executing API calls.

Your LLM prompts, embeddings, and job configurations are transmitted securely through a V8-isolated sandbox directly to your configured endpoint. Vinkius does not store the text payloads, ensuring your proprietary training data and API tokens remain private.

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