Runs chat and agent completions, transcribes audio, extracts text from scanned documents, and keeps a RAG document library up to date.
54actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro generates conversational responses from Mistral AI models to answer customer questions in real time. The customer receives a natural, context-aware reply instantly.
Ayro classifies chat content across 9 categories to enforce conversation safety policies automatically. The team maintains compliant interactions without manual review.
Ayro uploads documents to Mistral AI libraries for RAG-enabled agents to reference during conversations. The agent recalls company-specific knowledge to provide accurate, sourced answers.
Each card is one request a support team gets, and the Mistral.ai actions Ayro runs to close it.
Ayro generates a response from a Mistral chat model or from an agent that already carries its own instructions and tools, and checks the available base and fine-tuned models first when the request does not name one.
Ayro creates the agent with its instructions and tools, updates the configuration when the brief changes, and points a version alias at the release that should serve traffic.
Ayro uploads a document into the library an agent reads from, checks whether processing finished, and reprocesses one that came back wrong rather than leaving a stale answer in circulation.
Ayro runs OCR over a scanned invoice or form and transcribes an audio file to text, then screens the result through moderation before any of it reaches a customer reply.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Mistral.ai actions it has and picks the ones a request needs.
Authorize the Mistral.ai account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Mistral.ai actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeMistral.ai · Ayro
What can you do in Mistral.ai without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Mistral.ai.
The agent and conversation actions are the ones flagged beta in the toolkit itself, including Create Agent, Delete Agent, List Conversations, Restart Conversation, and Get Document Text Content. Ayro can call them, but they behave as Mistral's beta endpoints do and can change on Mistral's side.
All 54 actions your agent can call on Mistral.ai, straight from the live MCP connection.
Append new entries to an existing conversation in Mistral AI.
Create a new AI agent with custom configuration (Beta).
Generate completions using a Mistral AI agent with specific instructions and tools.
Transcribe audio files to text using Mistral AI's Voxtral models.
Generate conversational responses from Mistral AI models.
Classify chat content for moderation purposes across 9 categories.
Generate vector embeddings for input text using Mistral AI embedding models.
Generate code completions using fill-in-the-middle functionality.
Create a new document library.
Create or update sharing permissions for a library.
Classify text content for moderation purposes across 9 categories.
Extract text and structured data from images and documents using Mistral AI's OCR capabilities.
Create or update an agent version alias.
Permanently deletes an agent by its ID (Beta feature).
Delete a conversation by its ID (Beta).
Delete a file by its ID from Mistral AI.
Permanently deletes a library and all of its documents from Mistral AI.
Permanently deletes a document from a Mistral AI library.
Remove sharing permissions for a library from a user, workspace, or organization.
Download the content of a previously uploaded file from Mistral AI.
Retrieve details of a specific Mistral AI agent by its ID.
Retrieve a specific version of an agent (Beta).
Retrieve details of a specific conversation.
Retrieve the full history of a conversation in Mistral AI.
Retrieve all messages from a Mistral AI conversation.
Retrieve a signed URL to download the extracted text from a document in a Mistral AI library.
Get a signed URL to download a document from a Mistral AI library.
Retrieve the processing status of a document in a Mistral AI library.
Retrieve the extracted text content of a specific document from a Mistral AI library (Beta).
Get a time-limited signed URL for downloading a file from Mistral AI.
Same connection, same setup. Pick the next one your team already uses.
Pulls printed and handwritten text out of images a customer attaches, and transcribes audio clips into text the conversation can use.
Submits enhancement jobs, tracks them by hash, returns the finished result URL, and clears stored images once they are delivered.
Vets a model's card and security scan before adoption, runs inference, commits to Hub repositories, and watches repos through webhooks.
Lists 3D and AR embeds, orders modeling jobs, and reports completion percentage on the ones already in progress.
Detects the language an incoming message is written in and scores how closely two names or two addresses match before anything is acted on.
Runs pipelines singly or in bulk, stops an execution by run ID, and creates, inspects, or removes the chatbots built on top of them.

Authorize the account and your agent has all 54 actions from the first conversation.
