Mistral AI for AI agents
Mistral AI is a research lab providing open-weight and hosted large language models through an API for chat, embeddings, and OCR. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Mistral AI.
Generate a chat completion
Send a prompt to a Mistral model and get a completion for a drafting task.
Run OCR on a document
Extract text from a document image using Mistral's OCR capability, returning structured content for further use.
Approve before deleting a library
Require approval before deleting a document library, since it removes every indexed file in it.
105 Mistral AI actions, graded by risk.
Every Mistral AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
69Look things up. Allowed by default.
- mistral_ai.get_agentGet Agent
- mistral_ai.get_judgeGet Judge
- mistral_ai.get_modelGet Model
- mistral_ai.get_voiceGet Voice
- mistral_ai.list_filesList Files
- mistral_ai.get_datasetGet dataset
- mistral_ai.get_libraryGet library
- mistral_ai.list_agentsList Agents
- mistral_ai.list_judgesList Judges
- mistral_ai.list_modelsList Models
- mistral_ai.list_voicesList Voices
- mistral_ai.get_campaignGet campaign
- mistral_ai.get_workflowGet Workflow
- mistral_ai.get_batch_jobGet Batch Job
- mistral_ai.get_connectorGet Connector
- mistral_ai.list_datasetsList datasets
write
29Create and change things. Allow, or ask the user first.
- mistral_ai.create_ocrCreate OCR
- mistral_ai.create_agentCreate Agent
- mistral_ai.update_agentUpdate Agent
- mistral_ai.create_speechCreate Speech
- mistral_ai.create_libraryCreate library
- mistral_ai.update_libraryUpdate library
- mistral_ai.create_batch_jobCreate Batch Job
- mistral_ai.create_embeddingsCreate Embeddings
- mistral_ai.create_moderationCreate Moderation
- mistral_ai.create_library_shareCreate library share
- mistral_ai.update_agent_versionUpdate agent version
- mistral_ai.create_fim_completionCreate FIM Completion
- mistral_ai.create_chat_completionCreate Chat Completion
- mistral_ai.create_chat_moderationCreate Chat Moderation
- mistral_ai.update_fine_tuned_modelUpdate Fine-Tuned Model
- mistral_ai.update_library_documentUpdate library document
destructive
7Delete, cancel or archive. Ask first, or deny outright.
- mistral_ai.delete_fileDelete File
- mistral_ai.delete_agentDelete agent
- mistral_ai.delete_libraryDelete library
- mistral_ai.delete_conversationDelete Conversation
- mistral_ai.delete_library_shareDelete library share
- mistral_ai.delete_library_documentDelete library document
- mistral_ai.archive_fine_tuned_modelArchive Fine-Tuned Model
Mistral AI in three steps.
- 01Your users connect Mistral AIThey add their Mistral AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create OCR” can wait for the user, and “delete File” can be denied outright.
- 03Any agent can actYour agent calls Mistral AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mistral_ai', { read: 'allow', write: 'ask', // create_ocr destructive: 'deny', // delete_file }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mistral AI connects.
Users add their Mistral AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Mistral AI connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Mistral AI from any agent.
Mistral AI and Arc0, answered.
Can I use Mistral AI with Claude, ChatGPT or Cursor?
Yes. Connect Mistral AI to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Mistral AI actions you allow.
How do users connect Mistral AI?
Users add their Mistral AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Mistral AI actions can my agent take?
105 in total: 69 read, 29 write and 7 destructive, such as “create OCR”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Mistral AI?
Yes. Actions like “delete File” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Mistral AI too?
Yes. The same Mistral AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mistral AI into your agent.
Your users connect Mistral AI once, under your brand. Your agent gets 105 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan