How to Use the Mistral AI MCP in Google ADK

Q: Can my Google ADK agent manage files on Mistral AI for batch jobs?

Yes, your agent can upload files, list them using listfiles, and remove them with deletefile once processing is complete. This keeps your external storage footprint clean.

Q: How does Google ADK handle safety filtering with Mistral AI?

Your agent can pass user inputs to the moderate tool before sending them to Gemini or executing database writes. This adds an external safety layer to your enterprise pipeline.

Q: Can I restrict which Mistral AI tools are exposed to Google ADK?

Yes, you can use the toolnames filter during initialization to only expose specific tools like embeddings or chat. This prevents the agent from calling administrative actions on the MCP Server.

Connect Mistral AI tools to your Google ADK pipelines via this MCP Server to combine Gemini reasoning with specialized model endpoints.

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 Google ADK

Create your Vinkius account to connect Mistral AI to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bridge Google ADK agents with Mistral AI models

The `chat` tool allows your Google ADK agent to route specific reasoning subtasks to Mistral endpoints like codestral-latest. This lets your Gemini-powered supervisor agent delegate specialized coding or multilingual tasks to external models. By configuring the McpToolset, your agent discovers these endpoints dynamically. This MCP integration lets you filter the exposed tools using the tool_names parameter to keep the agent's context window clean.

Run high-volume background processing from BigQuery

The `create_batch` tool lets Google ADK agents process massive rows of BigQuery data asynchronously using Mistral's batch API. Your agent exports the data to a JSONL file, uploads it, and monitors progress using `list_batches`. If a data pipeline needs to be halted, the agent invokes `cancel_batch` to prevent unnecessary API charges. This architecture keeps your compute costs low while processing millions of records.

Generate vector embeddings for Vertex AI databases

The `embeddings` tool generates high-dimensional vector representations of text directly inside your Google ADK workflow. Your agent uses these vectors to perform semantic searches across your enterprise databases. You can feed these embeddings directly into Vertex AI search indexes. This connects your unstructured documents to your live agentic workflows without manual vector calculation.

Setup guide

Set up Mistral AI MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Mistral AI tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Mistral AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mistral AI tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You import McpToolset from the SDK and initialize it with your Vinkius HTTP transport URL. This registers the MCP tools directly into the agent's tool library.

Yes, your agent can upload files, list them using `list_files`, and remove them with `delete_file` once processing is complete. This keeps your external storage footprint clean.

Your agent can pass user inputs to the `moderate` tool before sending them to Gemini or executing database writes. This adds an external safety layer to your enterprise pipeline.

Yes, you can use the tool_names filter during initialization to only expose specific tools like `embeddings` or `chat`. This prevents the agent from calling administrative actions on the MCP Server.

Your raw text inputs and generated embedding vectors are transmitted over secure HTTPS directly to the model endpoints. The Vinkius sandbox executes these calls in ephemeral, isolated environments that immediately discard session data after the request completes.

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