How do I get a Mistral AI API Key?

Log in to the [**Mistral Console**](https://console.mistral.ai), go to **API Keys** in your workspace settings, click **Create new key** and copy it immediately. You'll need to set up billing in the admin portal first.

What models are available?

Use the `list_models` tool to see all available Mistral models. Key models include mistral-large-latest (most capable), mistral-small-latest (efficient), codestral-latest (code specialist), and mistral-embed for embeddings. Each has different context windows, capabilities and pricing.

Can I send multi-turn conversations?

Yes! Pass a messages array with alternating 'user', 'assistant' and 'system' roles. Each message has a 'role' and 'content' field. Mistral will continue the conversation based on the full message history.

Can I moderate content for safety?

Yes! Use the `moderate` tool with text input. It returns safety scores for categories including sexual, hate, violence, self-harm, criminal and other harmful content. This is useful for filtering user-generated content before processing.

Mistral AI MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Mistral AI
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Mistral AI through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Mistral AI "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Mistral AI?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Mistral AI MCP Server

Connect your Mistral AI account to any AI agent and leverage European-built AI models through natural conversation.

Pydantic AI validates every Mistral AI tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Model Discovery — List all available Mistral models with their IDs, capabilities and context windows
Chat Completions — Send conversations to Mistral models (large, small, codestral, nemo) and receive responses with configurable parameters
Embeddings — Generate vector embeddings for semantic search, similarity comparison and vector storage
Content Moderation — Check text for harmful categories (violence, hate, sexual, self-harm) with safety scores
File Management — List and delete uploaded files used for batch processing and document AI
Batch Processing — Create, track and cancel batch jobs for cost-effective asynchronous processing

The Mistral AI MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Mistral AI to Pydantic AI via MCP

Follow these steps to integrate the Mistral AI MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Mistral AI with type-safe schemas

Why Use Pydantic AI with the Mistral AI MCP Server

Pydantic AI provides unique advantages when paired with Mistral AI through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Mistral AI integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Mistral AI connection logic from agent behavior for testable, maintainable code

Mistral AI + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Mistral AI MCP Server delivers measurable value.

Type-safe data pipelines: query Mistral AI with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Mistral AI tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Mistral AI and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Mistral AI responses and write comprehensive agent tests

Mistral AI MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Mistral AI to Pydantic AI via MCP:

cancel_batch

Provide the batch ID. This is useful if you submitted a large batch by mistake and want to stop further processing. Cancel a running batch job

chat

Requires the model ID (e.g. "mistral-large-latest", "mistral-small-latest", "codestral-latest") and messages array in JSON format. Each message must have a "role" ("user", "assistant" or "system") and "content" (text). Optionally set max_tokens, temperature (0-1), top_p (0-1) and tools array for function calling. Returns the assistant's response. Send a chat message to a Mistral model

create_batch

Requires the input file ID (containing JSONL requests) and the endpoint (e.g. "/v1/chat/completions"). Returns the batch with its ID for tracking. Use list_batches and get_batch to monitor progress. Create a batch processing job

delete_file

Provide the file ID from list_files. WARNING: this action is irreversible. Delete an uploaded file from Mistral

embeddings

Requires the model ID and text input (string or array of strings). Returns embedding vectors for each input text. Useful for semantic search, similarity comparison and vector database storage. Generate embeddings using Mistral

get_batch

Provide the batch ID. Get details for a specific batch job

list_batches

Each batch shows its ID, status (queued, running, succeeded, failed, cancelled), input/output file IDs and request counts. List batch processing jobs

list_files

Files are used for fine-tuning, batch processing and document AI. Each file shows its ID, filename, purpose, size and upload date. List files uploaded to Mistral

list_models

Each model returns its ID (e.g. "mistral-large-latest", "mistral-small-latest", "codestral-latest"), display name, capabilities and context window. Use this to discover which models are available and their IDs for use with the chat tool. List all available Mistral AI models

moderate

). Requires the input text (string or array). Returns safety scores for each category. Useful for content filtering and safety checks before processing user input. Moderate text content with Mistral

Example Prompts for Mistral AI in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Mistral AI immediately.

"Send a message to Mistral Large asking 'What is the capital of France?'"

"List all available Mistral models."

"Moderate this text: 'I want to learn about AI safety and content filtering.'"

Troubleshooting Mistral AI MCP Server with Pydantic AI

Common issues when connecting Mistral AI to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Mistral AI + Pydantic AI FAQ

Common questions about integrating Mistral AI MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Mistral AI MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.