How to Use the Mistral AI MCP in VS Code Copilot

Q: Can I generate embeddings for my workspace files using Mistral AI and VS Code Copilot?

Yes. The agent invokes the embeddings tool to convert selected code blocks or documents into vector representations for semantic search.

Q: How do I track background batch jobs with Mistral AI in VS Code Copilot?

Your agent runs listbatches to display all active and completed jobs. You can query specific details for any job ID using the getbatch tool.

Q: Is there a way to see which Mistral models are currently supported?

Run the listmodels tool through Copilot to get a list of all available models, their display names, and their maximum context windows.

Connect VS Code Copilot to Mistral AI to run code generation, embeddings, and batch processing directly from your editor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mistral AI MCP to VS Code Copilot

Create your Vinkius account to connect Mistral AI 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 Mistral AI with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Code Generation and Chat inside VS Code Copilot

The `chat` tool routes your Copilot prompts directly to Mistral's endpoint, allowing you to test code generation against models like Codestral. Your agent queries `list_models` to verify available context windows and capabilities before sending the payload. This integration makes it easy to run multi-model comparisons. You can test how different LLMs handle your specific codebase structures without switching tools or leaving your editor.

Automate Content Moderation in Your Dev Pipelines

The `moderate` tool runs safety checks on user-generated content or code comments directly from your VS Code workspace. It evaluates text against safety categories and returns precise risk scores to your agent. You can build testing scripts that run this tool before committing code. It ensures your application's input validation logic aligns with Mistral's safety standards before deployment.

Manage Large-Scale Batch Runs with this MCP Server

The `create_batch` tool handles high-volume asynchronous jobs by submitting input files directly from your workspace. You monitor these jobs with `list_batches` and `get_batch` to track completion status. If a batch job fails or is no longer needed, the `cancel_batch` tool stops it immediately. You can clean up your workspace by listing files with `list_files` and removing them using `delete_file`.

Setup guide

Set up Mistral AI 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 Mistral AI 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 Mistral AI tools listed. Try asking: "List my recent Mistral AI transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "mistral-ai-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 Mistral AI. 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 Mistral AI 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 Mistral AI MCP in VS Code Copilot

Save the configuration to your settings file and commit it to your Git repository. Every developer on your team with VS Code 1.96+ will instantly gain access to the tools.

Yes. The agent invokes the `embeddings` tool to convert selected code blocks or documents into vector representations for semantic search.

Your agent runs `list_batches` to display all active and completed jobs. You can query specific details for any job ID using the `get_batch` tool.

Run the `list_models` tool through Copilot to get a list of all available models, their display names, and their maximum context windows.

All file metadata, batch payloads, and chat history are sent directly to Mistral's endpoints. Vinkius manages the connection through a zero-trust, ephemeral sandbox that never stores your 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