Mistral AI
for LuumenAI

Run Mistral models, agents, and document libraries from the terminal

Connect Mistral AI and Luumen can call chat, embedding, moderation, OCR, and transcription endpoints while you work, then read back agent and conversation state. Changes — creating an agent, sharing a library, starting or restarting a conversation — are previewed and held for your approval first. Authentication is by API key.

Book a DemoDownload Luumen

The Mistral AI toolbox

54 tools: 34 read, 20 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadCreate Agents CompletionGenerate completions using a Mistral AI agent with specific instructions and tools.
  • ReadCreate Audio TranscriptionTranscribe audio files to text using Mistral AI's Voxtral models.
  • ReadCreate Chat CompletionGenerate conversational responses from Mistral AI models.
  • ReadCreate Chat ModerationClassify chat content for moderation purposes across 9 categories.
  • ReadCreate EmbeddingsGenerate vector embeddings for input text using Mistral AI embedding models.
  • ReadCreate FIM CompletionGenerate code completions using fill-in-the-middle functionality.
  • ReadCreate ModerationClassify text content for moderation purposes across 9 categories.
  • ReadCreate OCRExtract text and structured data from images and documents using Mistral AI's OCR capabilities.
  • ReadDownload FileDownload the content of a previously uploaded file from Mistral AI.
  • ReadGet AgentRetrieve details of a specific Mistral AI agent by its ID.
  • ReadGet Agent VersionRetrieve a specific version of an agent (Beta).
  • ReadGet ConversationRetrieve details of a specific conversation.
  • ReadGet Conversation HistoryRetrieve the full history of a conversation in Mistral AI.
  • ReadGet Conversation MessagesRetrieve all messages from a Mistral AI conversation.
  • ReadGet document extracted text URLRetrieve a signed URL to download the extracted text from a document in a Mistral AI library.
  • ReadGet document signed URLGet a signed URL to download a document from a Mistral AI library.
  • ReadGet Document StatusRetrieve the processing status of a document in a Mistral AI library.
  • ReadGet Document Text ContentRetrieve the extracted text content of a specific document from a Mistral AI library (Beta).
  • ReadGet File Signed URLGet a time-limited signed URL for downloading a file from Mistral AI.
  • ReadList Fine Tuning JobsList fine-tuning jobs with optional filtering and pagination.
  • ReadGet libraryRetrieve detailed information about a specific library.
  • ReadGet Library DocumentRetrieve metadata for a specific document in a Mistral AI library.
  • ReadGet ModelRetrieve detailed information about a specific Mistral AI model by its ID.
  • ReadList agent aliasesRetrieve all aliases for an agent version.
  • ReadList AgentsList all configured agents (Beta).
  • ReadList Agent VersionsList all versions of a specific agent.
  • ReadList Batch JobsRetrieve a list of all batch jobs with optional filtering and pagination.
  • ReadList ConversationsList all created conversations (Beta).
  • ReadList FilesList all files available to the user.
  • ReadList librariesList all document libraries accessible to your organization.
  • ReadList Library DocumentsList all documents in a Mistral AI document library.
  • ReadList library sharesList all sharing permissions for a document library.
  • ReadList ModelsRetrieve all available Mistral AI models including base models and fine-tuned models.
  • ReadRetrieve FileRetrieve metadata of a file uploaded to Mistral AI.
  • WriteAppend to conversationAppend new entries to an existing conversation in Mistral AI. Approval by default
  • WriteCreate AgentCreate a new AI agent with custom configuration (Beta). Approval by default
  • WriteCreate libraryCreate a new document library. Approval by default
  • WriteCreate library shareCreate or update sharing permissions for a library. Approval by default
  • WriteCreate or Update Agent AliasCreate or update an agent version alias. Approval by default
  • WriteDelete agentPermanently deletes an agent by its ID (Beta feature). Approval by default
  • WriteDelete ConversationDelete a conversation by its ID (Beta). Approval by default
  • WriteDelete FileDelete a file by its ID from Mistral AI. Approval by default
  • WriteDelete libraryPermanently deletes a library and all of its documents from Mistral AI. Approval by default
  • WriteDelete library documentPermanently deletes a document from a Mistral AI library. Approval by default
  • WriteDelete library shareRemove sharing permissions for a library from a user, workspace, or organization. Approval by default
  • WriteReprocess documentReprocess a document in a Mistral AI library (Beta). Approval by default
  • WriteRestart ConversationRestart a conversation from a specific point (Beta). Approval by default
  • WriteStart ConversationStart a new conversation with a Mistral AI agent or base model. Approval by default
  • WriteUpdate AgentUpdate an existing agent's configuration. Approval by default
  • WriteUpdate agent versionUpdate the current version of an agent (Beta). Approval by default
  • WriteUpdate libraryUpdate an existing document library's properties. Approval by default
  • WriteUpdate library documentUpdate the metadata of a document in a Mistral AI library. Approval by default
  • WriteUpload FileUpload a file to Mistral AI for use in fine-tuning, batch processing, or OCR. Approval by default
  • WriteUpload Library DocumentUpload a document to a Mistral AI library for use with RAG-enabled agents. Approval by default

One prompt, start to finish

What a governed Mistral AI run looks like inside Luumen.

Questions

How does LuumenAI connect to Mistral AI?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Mistral AI on its own?

Read actions answer immediately. Anything that writes — append to conversation, create agent, create library, create library share, and more — is shown as a plan and requires approval by default, including the 6 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.

Who gets access to the integration?

You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.

Is there an audit trail?

Every call to Mistral AI — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task statusAffindaRead parsed documents, collections, and annotations — change them with approvalAgent MailGive the agent its own mailbox for reading threads and sending updatesAI/ML APIInspect assistants, threads, and runs — and change them as approved steps

Put Mistral AI to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.

Book a DemoDownload Luumen