Mistral.ai MCP integration
Runs chat and agent completions, transcribes audio, extracts text from scanned documents, and keeps a RAG document library up to date.
54actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create chat completion
Lyro generates conversational responses from Mistral AI models to answer customer questions in real time. The customer receives a natural, context-aware reply instantly.
Create chat moderation
Lyro classifies chat content across 9 categories to enforce conversation safety policies automatically. The team maintains compliant interactions without manual review.
Upload library document
Lyro 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.
How businesses use Mistral.ai + Lyro
Each card is one request a support team gets, and the Mistral.ai actions Lyro runs to close it.
Run a completion against the right model
Lyro 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.
Create Chat CompletionCreate Agents CompletionList ModelsBuild and version a Mistral agent
Lyro 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.
Create AgentUpdate AgentCreate or Update Agent AliasKeep a RAG library's documents current
Lyro 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.
Upload Library DocumentGet Document StatusReprocess DocumentTurn an attachment into text you can act on
Lyro 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.
Create OCRCreate Audio TranscriptionCreate Moderation
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Mistral.ai actions it has and picks the ones a request needs.
- 01
Connect Mistral.ai
Authorize the Mistral.ai account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Mistral.ai actions that close it and chains as many as the request needs.
- 03
Watch it work
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 free
Everything else about Mistral.ai
Setup, permissions, and the limits of what Lyro 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. Lyro can call them, but they behave as Mistral's beta endpoints do and can change on Mistral's side.
Every action available in Mistral.ai
All 54 actions your agent can call on Mistral.ai, straight from the live MCP connection.
Append to conversation
Append new entries to an existing conversation in Mistral AI.
Create agent
Create a new AI agent with custom configuration (Beta).
Create agents completion
Generate completions using a Mistral AI agent with specific instructions and tools.
Create audio transcription
Transcribe audio files to text using Mistral AI's Voxtral models.
Create chat completion
Generate conversational responses from Mistral AI models.
Create chat moderation
Classify chat content for moderation purposes across 9 categories.
Create embeddings
Generate vector embeddings for input text using Mistral AI embedding models.
Create fim completion
Generate code completions using fill-in-the-middle functionality.
Create library
Create a new document library.
Create library share
Create or update sharing permissions for a library.
Create moderation
Classify text content for moderation purposes across 9 categories.
Create ocr
Extract text and structured data from images and documents using Mistral AI's OCR capabilities.
Create or update agent alias
Create or update an agent version alias.
Delete agent
Permanently deletes an agent by its ID (Beta feature).
Delete conversation
Delete a conversation by its ID (Beta).
Delete file
Delete a file by its ID from Mistral AI.
Delete library
Permanently deletes a library and all of its documents from Mistral AI.
Delete library document
Permanently deletes a document from a Mistral AI library.
Delete library share
Remove sharing permissions for a library from a user, workspace, or organization.
Download file
Download the content of a previously uploaded file from Mistral AI.
Get agent
Retrieve details of a specific Mistral AI agent by its ID.
Get agent version
Retrieve a specific version of an agent (Beta).
Get conversation
Retrieve details of a specific conversation.
Get conversation history
Retrieve the full history of a conversation in Mistral AI.
Get conversation messages
Retrieve all messages from a Mistral AI conversation.
Get document extracted text URL
Retrieve a signed URL to download the extracted text from a document in a Mistral AI library.
Get document signed URL
Get a signed URL to download a document from a Mistral AI library.
Get document status
Retrieve the processing status of a document in a Mistral AI library.
Get document text content
Retrieve the extracted text content of a specific document from a Mistral AI library (Beta).
Get file signed URL
Get a time-limited signed URL for downloading a file from Mistral AI.
The tools Mistral.ai sits next to
Same connection, same setup. Pick the next one your team already uses.
Astica.ai
Pulls printed and handwritten text out of images a customer attaches, and transcribes audio clips into text the conversation can use.
DeepImage
Submits enhancement jobs, tracks them by hash, returns the finished result URL, and clears stored images once they are delivered.
Hugging Face
Vets a model's card and security scan before adoption, runs inference, commits to Hub repositories, and watches repos through webhooks.
Modelry
Lists 3D and AR embeds, orders modeling jobs, and reports completion percentage on the ones already in progress.
Rosette text analytics
Detects the language an incoming message is written in and scores how closely two names or two addresses match before anything is acted on.
Vectorshift
Runs pipelines singly or in bulk, stops an execution by run ID, and creates, inspects, or removes the chatbots built on top of them.

Ready to connect Mistral.ai?
Authorize the account and your agent has all 54 actions from the first conversation.


