How to Use the Mistral AI MCP in Claude

Q: Can I use Mistral AI models to generate embeddings directly in Claude Desktop?

Yes. Your agent uses the embeddings tool to convert text blocks into vector representations inside your chat window, making it easy to prepare data for your vector databases.

Q: What is the easiest way to manage Mistral AI batch jobs using Claude Desktop?

You can instruct your agent to run createbatch with an uploaded file ID. From there, the agent monitors progress using listbatches and getbatch without requiring terminal commands.

Q: How do I clean up files I uploaded for processing?

Use the listfiles tool to locate your target file ID. Once identified, call deletefile to permanently purge that file from the remote servers.

Query Mistral AI models, generate embeddings, and run massive batch jobs directly from your Claude Desktop interface.

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 Claude Desktop

Create your Vinkius account to connect Mistral AI to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Mistral AI Models inside Claude Desktop

The `chat` tool lets you execute inference directly against Mistral's model lineup, including Mistral Large and Codestral, without leaving your workspace. Your agent queries the `list_models` tool to discover what models are online and immediately routes your prompts to them. This bypasses the need for manual API key routing or switching browser tabs. You get raw model outputs fed straight into your conversation window, allowing you to compare alternative LLM outputs side-by-side with Claude's native responses.

Run High-Volume Batch Operations

The `create_batch` tool handles asynchronous processing by letting you submit massive JSONL files for offline computation. When you need to monitor or stop these jobs, the server exposes `list_batches`, `get_batch`, and `cancel_batch` to keep you in control. You don't have to write custom Python scripts to poll the API state. Your agent checks the status of your jobs in the background and alerts you when the results are ready for download.

Secure Your Inputs with Native Moderation

The `moderate` tool screens user inputs and model outputs against safety categories to flag policy violations before they cause issues. It works alongside `embeddings` to convert your text into vector representations for semantic search and classification. This setup runs entirely through the Vinkius MCP Server sandbox. You can clean up your workspace afterward by using `list_files` and `delete_file` to remove sensitive training data permanently from Mistral's servers.

Setup guide

Set up Mistral AI MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Mistral AI MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Mistral AI MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under mistral-ai-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 Claude Desktop

Open your configuration file via the developer settings. Add the server entry under the mcpServers key with your Vinkius credentials, save, and restart Claude to load the tools.

Yes. Your agent uses the `embeddings` tool to convert text blocks into vector representations inside your chat window, making it easy to prepare data for your vector databases.

You can instruct your agent to run `create_batch` with an uploaded file ID. From there, the agent monitors progress using `list_batches` and `get_batch` without requiring terminal commands.

Use the `list_files` tool to locate your target file ID. Once identified, call `delete_file` to permanently purge that file from the remote servers.

Vinkius runs this integration inside an isolated V8 sandbox. Your API keys, chat payloads, and batch files are processed in ephemeral environments, meaning no data persists on the host platform after execution.

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