How to Use the Cerebras Inference MCP in VS Code Copilot

Q: How can my team share a Cerebras Inference configuration for VS Code Copilot?

Create a .vscode/mcp.json file in your project's root. Add the Cerebras MCP Server details there and commit it to Git. Every team member who clones the repo will automatically get the tools in Copilot.

Q: Can I run a Cerebras Inference batch job from VS Code Copilot?

Yes. First, use the uploadfile tool to send your JSONL data. Then, ask the Copilot agent to start a job using createbatch. You can check its progress with getbatch.

Q: Is it possible to manage files for Cerebras Inference batch jobs within VS Code Copilot?

Yes. The server provides listfiles, getfilecontent, and deletefile. You can ask the Copilot agent to list all uploaded files or download the content of a specific result file into your editor.

Equip your whole team with Cerebras inference tools inside VS Code. Share one config, get consistent Copilot agent behavior across the board.

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 VS Code Copilot

Create your Vinkius account to connect Cerebras Inference to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Inference for Your Team

Here's the point: add the Cerebras MCP Server to `.vscode/mcp.json` and commit it. Now every developer on the team gets the same tools. No more "it works on my machine" issues with API scripts. When a new developer clones the repo, Copilot is ready. They can immediately ask the agent to run a text generation with `create_completion` or check available models with `list_models`, using the exact same config as everyone else. It's infrastructure-as-code for your agent's tools.

Manage Cerebras Resources from VS Code

You're working on a feature that uses batch processing. You can use Copilot Chat to upload a test file with `upload_file`, start a job with `create_batch`, and monitor it with `get_batch`. This isn't just for chat. You can use these tools to debug. If a job fails, ask Copilot to "get the content of the result file for batch 123." It can use `get_file_content` to pull that data directly into a new editor tab. You don't have to leave VS Code to see what went wrong.

Your VS Code MCP Server for Model Ops

This is a great tool for MLOps and platform engineers. You can quickly check the health of the inference endpoints by asking Copilot to run `get_metrics`. The Prometheus-formatted output appears right in the chat. You can also manage the models. Ask Copilot to get details on a new model with `get_model` or compare it against the public list from `list_public_models`. This turns Copilot from just a code assistant into a control plane for your AI stack.

Setup guide

Set up Cerebras Inference MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Cerebras Inference MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Cerebras Inference tools listed. Try asking: "List my recent Cerebras Inference transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

Create a `.vscode/mcp.json` file in your project's root. Add the Cerebras MCP Server details there and commit it to Git. Every team member who clones the repo will automatically get the tools in Copilot.

Yes. First, use the `upload_file` tool to send your `JSONL` data. Then, ask the Copilot agent to start a job using `create_batch`. You can check its progress with `get_batch`.

When you ask the agent "what models are available?", it calls the `list_models` tool on the MCP Server. The agent then presents the list of models directly in the chat panel for you to choose from.

Yes. The server provides `list_files`, `get_file_content`, and `delete_file`. You can ask the Copilot agent to list all uploaded files or download the content of a specific result file into your editor.

Only the data required for a tool to run is sent over the wire. This means the prompt for `create_completion` or a `JSONL` file for `upload_file`. This data is processed in an isolated Vinkius environment and is never co-mingled with other customers' data. All traffic is encrypted end-to-end.

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