Mistral AI MCP integration for AI agents.

Connect AI agents to Mistral AI through 54 structured actions, including download file, create agent, delete agent, and append to conversation. Review authen…

ACTION CONTRACTS
54
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Mistral AI integration exposes

The Mistral AI Agent App exposes 54 provider-backed actions for ai work. Its current contract lets an authorized agent download mistral file contents into the local transit file store, create a new mistral agent, and delete the specified agent. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Mistral AI account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Mistral AI capabilities.

Showing 12 of 54 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

download_fileREAD

Download Mistral file contents into the local transit file store.

INPUTS: file_id

create_agentWRITE

Create a new Mistral agent.

INPUTS: model / name / instructions / tools / completion_args

delete_agentHIGH IMPACT

Delete the specified agent.

INPUTS: agent_id

append_to_conversationREVIEW

Append a new message to an existing conversation.

INPUTS: conversation_id / inputs / completion_args / handoff_execution / store

create_agents_completionWRITE

Call the Mistral agents completions API.

INPUTS: agent_id / messages / temperature / top_p / max_tokens

create_audio_transcriptionWRITE

Upload or reference audio and create a transcription.

INPUTS: file / file_id / context_bias / diarize / language

create_chat_completionWRITE

Call the Mistral chat completions API.

INPUTS: model / messages / temperature / top_p / max_tokens

create_chat_moderationWRITE

Detect chat message safety risks with Mistral moderation.

INPUTS: model / input

create_embeddingsWRITE

Generate embeddings with Mistral.

INPUTS: model / input / metadata / output_dimension / output_dtype

create_fim_completionWRITE

Call the Mistral FIM completions API.

INPUTS: model / prompt / suffix / temperature / top_p

create_libraryWRITE

Create a new Mistral library.

INPUTS: name / description / chunk_size

create_library_shareWRITE

Create or update shared access for a library.

INPUTS: library_id / level / org_id / share_with_uuid / share_with_type

INPUT CONTRACTS

Know what the action needs before it runs.

download_file

file_idREQUIRED
File ID.

create_agent

modelREQUIRED
The default model used by the agent.
nameREQUIRED
Agent name.
instructionsOPTIONAL
Agent instructions.
toolsOPTIONAL
Tools available to the agent.
completion_argsOPTIONAL
Completion parameter configuration accepted by Mistral.

delete_agent

agent_idREQUIRED
Agent ID.

append_to_conversation

conversation_idREQUIRED
Conversation ID.
inputsREQUIRED
Input to append to the conversation.
completion_argsOPTIONAL
Completion parameter configuration accepted by Mistral.
handoff_executionOPTIONAL
Handoff execution method.
storeOPTIONAL
Whether to persist storage.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Download File

Download Mistral file contents into the local transit file store. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

download_file

Control Create Agent

Create a new Mistral agent. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

create_agent

Verify with Create Agent

Create a new Mistral agent. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

create_agent

SAFETY BOUNDARY

Operate Mistral AI with explicit limits

  • Authorize Mistral AI with API key and grant only the provider access required by the selected actions.
  • 25 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
  • Treat `delete_agent`, `delete_conversation`, and `delete_file` as high-impact operations and require an explicit approval boundary.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Mistral AI rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Mistral AI task completed successfully.

CONNECTION MODEL

API key

Mistral API key used with the Authorization Bearer header. Create or manage keys in the Mistral Console: https://console.mistral.ai/api-keys/.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
26
WRITE SIGNALS
19
HIGH IMPACT
6
REVIEW SIGNALS
3

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Mistral AI.

Official Mistral AI website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS