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 LlamaIndex 10 tools — connect in under 2 minutes

Name: Mistral AI
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Mistral AI as an MCP tool provider through the Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

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 llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Mistral AI. "
            "You have 10 tools available."
        ),
    )

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

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.

LlamaIndex agents combine Mistral AI tool responses with indexed documents for comprehensive, grounded answers. Connect 10 tools through the Vinkius and query live data alongside vector stores and SQL databases in a single turn — ideal for hybrid search, data enrichment, and analytical workflows.

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 LlamaIndex 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 LlamaIndex via MCP

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

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

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

Why Use LlamaIndex with the Mistral AI MCP Server

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

Data-first architecture: LlamaIndex agents combine Mistral AI tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Mistral AI tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Mistral AI, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Mistral AI tools were called, what data was returned, and how it influenced the final answer

Mistral AI + LlamaIndex Use Cases

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

Hybrid search: combine Mistral AI real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Mistral AI to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Mistral AI for fresh data

Analytical workflows: chain Mistral AI queries with LlamaIndex's data connectors to build multi-source analytical reports

Mistral AI MCP Tools for LlamaIndex (10)

These 10 tools become available when you connect Mistral AI to LlamaIndex 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 LlamaIndex

Ready-to-use prompts you can give your LlamaIndex 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 LlamaIndex

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

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Mistral AI + LlamaIndex FAQ

Common questions about integrating Mistral AI MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Mistral AI tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.