How to Use the Cerebras Inference MCP in Windsurf

Q: Where do I add the Cerebras Inference MCP Server API key inside Windsurf?

You configure it in your /.codeium/windsurf/mcpconfig.json file under the mcpServers block. Once saved, Windsurf establishes the connection and Cascade auto-discovers all fifteen tools.

Run instant LLM completions and manage batch jobs directly from Windsurf using Cascade's autonomous multi-step execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cerebras Inference MCP to Windsurf

Create your Vinkius account to connect Cerebras Inference 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 Cerebras Inference with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run batch inference pipelines with Windsurf Cascade

The `create_batch` tool lets Cascade set up large-scale offline runs without waiting on individual API calls. Cascade handles the file preparation, runs `upload_file` to send your JSONL data, and initiates the run. Once the run starts, Cascade monitors progress by calling `get_batch` in the background. It downloads the final results using `get_file_content` and writes them straight to your local directory when done.

Let Cascade query live Cerebras models

The `list_models` tool gives your IDE a live feed of every active Cerebras model size and variant. Cascade reads this list to choose the fastest endpoint for your current task. If you do not have your API key set up yet, Cascade uses `list_public_models` to check what's open. It swaps models on the fly in your configurations based on what it finds.

Trigger fast completions inside this MCP Server

The `create_chat_completion` tool connects Windsurf directly to the Cerebras wafer-scale engine for sub-second text generation. Cascade uses this to test prompts, write documentation, or generate code blocks instantly. You get raw speed because the server bypasses standard rate-limiting queues. Cascade pipes the output directly into your active editor window.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "cerebras-inference-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 Cerebras Inference. 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 Cerebras Inference 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 Cerebras Inference MCP in Windsurf

It connects Cascade to wafer-scale chips that run completions at hundreds of tokens per second. Cascade can write, test, and refactor code without the normal lag you get from standard cloud models.

Yes. Cascade uses the batch tools to write local JSONL data, push it to the server, and monitor the processing queue until everything is parsed and saved.

You configure it in your ~/.codeium/windsurf/mcp_config.json file under the mcpServers block. Once saved, Windsurf establishes the connection and Cascade auto-discovers all fifteen tools.

You can tell your agent to cancel it. The agent calls the cancel tool to stop processing on the wafer immediately, saving your API credits.

Your JSONL files and chat payloads go directly to the Cerebras API endpoints over encrypted connections. Vinkius runs this server in an isolated, ephemeral sandbox, so no local data is stored or cached after the request completes.

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