--- title: "Mistral AI MCP server for AI agents - actionlake" description: "Give Claude 306 Mistral AI actions through one MCP server: rag managed indexes. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/mistral-ai updated: 2026-10-23 --- Connectors · AI # Mistral AI MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Mistral AI and the rest of your systems. It gives your agent 306 Mistral AI actions (151 reads, 109 writes and 46 that wait for a confirmation) and holds the Mistral AI credential itself, so the agent never does. It paces Mistral AI's limits and records every call. [Connect Mistral AI free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "mistral.admin_users.list", intent: "check which Mistral AI account is connected" } # Get Users · read · 1 upstream call ``` - 306 actions in one signed file - 151 read look, never change - 109 write create and update - 46 wait for a yes destructive, confirmed first Set up ## Connect Mistral AI in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Mistral AI. API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `api_key` Mistral API key (console.mistral.ai > API Keys) ``` account { op: "connections.requirements", service: "mistral" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "mistral.admin_users.list" } # get users · read · 1 upstream call check { action: "mistral.admin_users.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Mistral AI at a glance **Sign-in** API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `api_key` **Limits we pace to** 60 calls a minute, per connection **API covered** Mistral AI API 1.0.0`api.mistral.ai` **Built from** Mistral AI's documentation, read 23 October 2026[docs.mistral.ai](https://docs.mistral.ai/openapi.yaml) [docs.mistral.ai](https://docs.mistral.ai/api/) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 122 of 151 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 6, so ask can line Mistral AI up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Mistral AI. 306 actions in 131 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **151** read look, never change - **109** write create and update - **46** destructive wait for a confirmation 1. ### Rag managed indexes 9 6 read · 2 write · 1 destructive Create a managed index · List managed indexes · Get a managed index · Update a managed index schema 2. ### Workflows deployments 9 2 read · 6 write · 1 destructive Create Deployment · List Deployments · Get Deployment · Update Deployment 3. ### Workflows executions 9 2 read · 3 write · 4 destructive Get Workflow Execution · Query Workflow Execution · Reset Workflow · Signal Workflow Execution 4. ### Workflows 8 2 read · 5 write · 1 destructive Get Workflows · Get Workflow · Update Workflow · Execute Workflow 5. ### Workflows schedules 8 2 read · 4 write · 2 destructive Schedule Workflow · Get Schedules · Get Schedule · Update Schedule 6. ### Connectors 7 2 read · 4 write · 1 destructive Create a new connector. · List all connectors. · Get a connector. · Update a connector. 7. ### Admin user groups 6 2 read · 3 write · 1 destructive Get User Groups · Create User Group · Get User Group · Update User Group 8. ### Admin users 6 2 read · 2 write · 2 destructive Get Users · Create Users · Get User · Update User **123 more areas · 244 actions** - Admin workspaces **6** - Conversations **6** - Libraries **6** - Libraries documents **6** - Observability datasets **6** - Observability judges **6** - Agents **5** - Audio voices **5** - Batch jobs **5** - Observability pipelines **5** - Prompts **5** - Service accounts **5** - Skills **5** - Admin user groups workspaces **4** - Observability dataset records **4** - Observability datasets imports **4** - Prompts versions **4** - Skills versions **4** - Admin API keys **3** - Admin user groups members **3** - Admin user invites **3** - Agents aliases **3** - Connectors credentials **3** - Files **3** - Fine tuning models **3** - Libraries share **3** - Models **3** - Observability spans evaluations **3** - Observability traces **3** - Rag deployments **3** - Workflows registrations **3** - Admin scim sync **2** - Admin spend limit **2** - Admin usage **2** - Admin user groups nested **2** - Agents versions **2** - Connectors organization share **2** - Connectors share **2** - Connectors tools **2** - Connectors user credentials **2** - Observability datasets records **2** - Observability datasets tasks **2** - Observability evaluation runs V2 **2** - Observability evaluation runs V2 records **2** - Observability evaluation runs V2 statistics **2** - Observability optimizations **2** - Observability projects **2** - Observability spans **2** - Observability traces spans **2** - Rag ingestion pipeline configurations **2** - Rag managed indexes documents **2** - Service accounts roles **2** - Workflows runs **2** - Admin analytics vibe code usage by organization **1** - Admin analytics vibe code usage by workspace **1** - Admin analytics vibe work usage by agent stats **1** - Admin analytics vibe work usage by time stats **1** - Admin analytics vibe work usage by user stats **1** - Admin audit logs **1** - Admin rate limit **1** - Admin roles **1** - Admin user groups organization role **1** - Admin workspaces users **1** - Agents completions **1** - Agents pages **1** - Agents version **1** - Audio speech **1** - Audio voices V2 **1** - Chat classifications **1** - Chat completions **1** - Chat moderations **1** - Classifications **1** - Connectors auth URL **1** - Connectors authentication methods **1** - Connectors organization credentials **1** - Connectors workspace credentials **1** - Conversations history **1** - Conversations messages **1** - Embeddings **1** - Files URL **1** - Fim completions **1** - Libraries documents extracted text signed URL **1** - Libraries documents signed URL **1** - Libraries documents status **1** - Libraries documents text content **1** - Moderations **1** - Observability dataset records payload **1** - Observability dataset records properties **1** - Observability evaluations V2 **1** - Observability evaluations V2 runs **1** - Observability logs **1** - Observability logs fields **1** - Observability logs fields options **1** - Observability optimizations trials **1** - Observability pipeline results **1** - Observability projects evaluations V2 **1** - Observability spans evaluations fields **1** - Observability spans evaluations fields options **1** - Observability spans fields **1** - Observability spans fields options **1** - Observability traces fields **1** - Observability traces fields options **1** - Ocr **1** - Rag deployments metrics **1** - Rag ingestion pipeline configurations run info **1** - Rag managed indexes chunks **1** - Realtime client sessions **1** - Service accounts assignable roles **1** - Users me **1** - Users me organizations **1** - Users me workspaces **1** - Whoami **1** - Workflows deployments logs **1** - Workflows deployments workers **1** - Workflows events **1** - Workflows executions history **1** - Workflows executions logs **1** - Workflows executions trace events **1** - Workflows executions trace info **1** - Workflows executions trace otel **1** - Workflows executions trace summary **1** - Workflows metrics **1** - Workflows runs history **1** Top actions ## The Mistral AI API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 46 of Mistral AI's 46 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `mistral.admin_users.list` Get Users | Get Users | read | `identity.user.list` 474 connectors | | `mistral.admin_user_groups.list` Get User Groups | Get User Groups | read | `identity.group.list` 262 connectors | | `mistral.users_me.get` Get Identity | Get Identity | read | `identity.current_user.get` 307 connectors | | `mistral.admin_users.create` Create Users | Create Users | write | `identity.user.create` 262 connectors | | `mistral.service_accounts.list` List Service Accounts | List Service Accounts | read | `identity.service_account.list` 35 connectors | | `mistral.admin_user_groups.create` Create User Group | Create User Group | write | `identity.group.create` 205 connectors | | `mistral.service_accounts.create` Create Service Account | Create Service Account | write | `identity.service_account.create` 32 connectors | | `mistral.files.list` List Files | List Files | read | `content.file.list` 77 connectors | | `mistral.admin_workspaces.list` Get Workspaces | Get Workspaces | read | `work.workspace.list` 50 connectors | | `mistral.admin_roles.get` Get Roles | Get Roles | read | `identity.role.list` 184 connectors | | `mistral.admin_user_groups_members.list` Get User Group Members | Get User Group Members | read | `identity.group_member.list` 103 connectors | | `mistral.admin_api_keys.create` Create Api Key | Create Api Key | destructive | `identity.api_key.create` 100 connectors | Try it ## Prompts to paste into Claude. Each one names the Mistral AI actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which Mistral AI files changed this week, and who changed them? calls `mistral.files.list` 2. Write write Create Users in Mistral AI. Show me exactly what you will send before you save it. calls `mistral.admin_users.create` Governance for Mistral AI ## Destructive actions wait for a yes. 46 Mistral AI actions are destructive. The first 10: - Delete User `mistral.admin_users.delete` - Delete User Group `mistral.admin_user_groups.delete` - Create Api Key `mistral.admin_api_keys.create` - Delete Service Account `mistral.service_accounts.delete` - Delete Api Key `mistral.admin_api_keys.delete` - Delete File `mistral.files.delete` - Delete Invite `mistral.admin_user_invites.delete` - Delete Workspaces `mistral.admin_workspaces.delete` - Remove Users From Group `mistral.admin_user_groups_members.remove` - Delete Model `mistral.models.delete` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do mistral.admin_users.delete confirm_policy: **human** Delete User? **intent:** the user asked me to delete User run suspended · waiting for a named person · key _mistral-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "mistral-agent", allowed_actions: ["mistral.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "mistral.admin_users.delete", approver: "lead@example.com" }, { match: "mistral.admin_user_groups.delete", approver: "lead@example.com" }, { match: "mistral.admin_api_keys.create", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Mistral AI only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Mistral AI costs on actionlake. Every Mistral AI action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Mistral AI refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 306 Mistral AI actions - 69 actions page each page of a long list is one call - 122 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Mistral AI action. 306 actions by area: the id your agent calls, what it does, and its effect. **Rag managed indexes 9** - `mistral.rag_managed_indexes.create` Create a managed index write - `mistral.rag_managed_indexes.get` Get a managed index read - `mistral.rag_managed_indexes.list` List managed indexes read - `mistral.rag_managed_indexes.update` Update a managed index schema write - `mistral.rag_managed_indexes.delete` Delete a managed index destructive - `mistral.rag_managed_indexes.grep` Grep for a pattern within a source read - and 3 more in this area **Workflows deployments 9** - `mistral.workflows_deployments.create` Create Deployment write - `mistral.workflows_deployments.get` Get Deployment read - `mistral.workflows_deployments.list` List Deployments read - `mistral.workflows_deployments.update` Update Deployment write - `mistral.workflows_deployments.delete` Delete Deployment destructive - `mistral.workflows_deployments.restart` Restart Deployment write - and 3 more in this area **Workflows executions 9** - `mistral.workflows_executions.get` Get Workflow Execution read - `mistral.workflows_executions.query` Query Workflow Execution read - `mistral.workflows_executions.reset` Reset Workflow write - `mistral.workflows_executions.signals` Signal Workflow Execution write - `mistral.workflows_executions.batch_cancel` Batch Cancel Workflow Executions destructive - `mistral.workflows_executions.batch_terminate` Batch Terminate Workflow Executions destructive - and 3 more in this area **Workflows 8** - `mistral.workflows.execute` Execute Workflow destructive - `mistral.workflows.get` Get Workflow read - `mistral.workflows.list` Get Workflows read - `mistral.workflows.update` Update Workflow write - `mistral.workflows.archive` Archive Workflow write - `mistral.workflows.archive_many` Bulk Archive Workflows write - and 2 more in this area **Workflows schedules 8** - `mistral.workflows_schedules.create` Schedule Workflow write - `mistral.workflows_schedules.get` Get Schedule read - `mistral.workflows_schedules.list` Get Schedules read - `mistral.workflows_schedules.update` Update Schedule write - `mistral.workflows_schedules.delete` Unschedule Workflow destructive - `mistral.workflows_schedules.pause` Pause Schedule write - and 2 more in this area **Connectors 7** - `mistral.connectors.create` Create a new connector. write - `mistral.connectors.get` Get a connector. read - `mistral.connectors.list` List all connectors. read - `mistral.connectors.update` Update a connector. write - `mistral.connectors.activate` Activate a connector for the given consumer (organization, workspace, user). write - `mistral.connectors.deactivate` Deactivate a connector for the current consumer (at organization, workspace or user level). write - and 1 more in this area **Admin user groups 6** - `mistral.admin_user_groups.create` Create User Group write - `mistral.admin_user_groups.get` Get User Group read - `mistral.admin_user_groups.list` Get User Groups read - `mistral.admin_user_groups.update` Update User Group write - `mistral.admin_user_groups.delete` Delete User Group destructive - `mistral.admin_user_groups.provision_workspace` Provision Group To Workspace write **Admin users 6** - `mistral.admin_users.create` Create Users write - `mistral.admin_users.get` Get User read - `mistral.admin_users.list` Get Users read - `mistral.admin_users.update` Update User write - `mistral.admin_users.deactivate` Deactivate User destructive - `mistral.admin_users.delete` Delete User destructive **Admin workspaces 6** - `mistral.admin_workspaces.create` Create Workspace write - `mistral.admin_workspaces.delete` Delete Workspaces destructive - `mistral.admin_workspaces.list` Get Workspaces read - `mistral.admin_workspaces.update` Update Workspaces write - `mistral.admin_workspaces.add_users` Add Users Workspaces write - `mistral.admin_workspaces.remove_users` Remove Users Workspaces destructive **Conversations 6** - `mistral.conversations.create` Create a conversation and append entries to it. write - `mistral.conversations.delete` Delete a conversation. destructive - `mistral.conversations.get` Retrieve a conversation information. read - `mistral.conversations.list` List all created conversations. read - `mistral.conversations.append` Append new entries to an existing conversation. write - `mistral.conversations.restart` Restart a conversation starting from a given entry. write **Libraries 6** - `mistral.libraries.create` Create a new Library. write - `mistral.libraries.get` Detailed information about a specific Library. read - `mistral.libraries.list` List all libraries you have access to. read - `mistral.libraries.update` Update a library. write - `mistral.libraries.update_legacy` Update a library. write - `mistral.libraries.delete` Delete a library and all of it's document. destructive **Libraries documents 6** - `mistral.libraries_documents.delete` Delete a document. destructive - `mistral.libraries_documents.get` Retrieve the metadata of a specific document. read - `mistral.libraries_documents.list` List documents in a given library. read - `mistral.libraries_documents.update` Update the metadata of a specific document. write - `mistral.libraries_documents.update_legacy` Update the metadata of a specific document. write - `mistral.libraries_documents.reprocess` Reprocess a document. write **Observability datasets 6** - `mistral.observability_datasets.create` Create a new empty dataset write - `mistral.observability_datasets.get` Get dataset by ID or slug read - `mistral.observability_datasets.list` List existing datasets read - `mistral.observability_datasets.update` Patch dataset write - `mistral.observability_datasets.delete` Delete a dataset destructive - `mistral.observability_datasets.export_jsonl` Export to the Files API and retrieve presigned URL to download the resulting JSONL file read **Observability judges 6** - `mistral.observability_judges.create` Create a new judge write - `mistral.observability_judges.get` Get judge by id read - `mistral.observability_judges.list` Get judges with optional filtering and search read - `mistral.observability_judges.update` Update a judge write - `mistral.observability_judges.delete` Delete a judge destructive - `mistral.observability_judges.live_judging` Run a saved judge on a conversation write **Agents 5** - `mistral.agents.create` Create an agent that can be used within a conversation. write - `mistral.agents.delete` Delete an agent entity. destructive - `mistral.agents.get` Retrieve an agent entity. read - `mistral.agents.list` List agent entities. read - `mistral.agents.update` Update an agent entity. write **Audio voices 5** - `mistral.audio_voices.create` Create a new voice write - `mistral.audio_voices.get` Get voice details read - `mistral.audio_voices.list` List all voices read - `mistral.audio_voices.update` Update voice metadata write - `mistral.audio_voices.delete` Delete a custom voice destructive **Batch jobs 5** - `mistral.batch_jobs.cancel` Cancel Batch Job destructive - `mistral.batch_jobs.create` Create Batch Job write - `mistral.batch_jobs.get` Get Batch Job read - `mistral.batch_jobs.list` Get Batch Jobs read - `mistral.batch_jobs.delete` Delete Batch Job destructive **Observability pipelines 5** - `mistral.observability_pipelines.create` Create a pipeline write - `mistral.observability_pipelines.get` Get a pipeline read - `mistral.observability_pipelines.list` List pipelines read - `mistral.observability_pipelines.update` Update a pipeline write - `mistral.observability_pipelines.delete` Delete a pipeline destructive **Prompts 5** - `mistral.prompts.create` CreatePrompt write - `mistral.prompts.get` GetPrompt read - `mistral.prompts.list` ListPrompts read - `mistral.prompts.update` UpdatePrompt write - `mistral.prompts.delete` DeletePrompt destructive **Service accounts 5** - `mistral.service_accounts.create` Create Service Account write - `mistral.service_accounts.get` Get Service Account read - `mistral.service_accounts.list` List Service Accounts read - `mistral.service_accounts.update` Update Service Account write - `mistral.service_accounts.delete` Delete Service Account destructive **Skills 5** - `mistral.skills.create` CreateSkill write - `mistral.skills.get` GetSkill read - `mistral.skills.list` ListSkills read - `mistral.skills.update` UpdateSkill write - `mistral.skills.delete` DeleteSkill destructive **Admin user groups workspaces 4** - `mistral.admin_user_groups_workspaces.assign` Assign Group To Workspace write - `mistral.admin_user_groups_workspaces.delete` Remove Group From Workspace destructive - `mistral.admin_user_groups_workspaces.list` Get Group Workspace Assignments read - `mistral.admin_user_groups_workspaces.update` Update Group Workspace Assignment write **Observability dataset records 4** - `mistral.observability_dataset_records.bulk_delete` Delete multiple records from datasets destructive - `mistral.observability_dataset_records.delete` Delete a record from a dataset destructive - `mistral.observability_dataset_records.get` Get the content of a given dataset record read - `mistral.observability_dataset_records.live_judging` Run Judge on a dataset record based on the given options write **Observability datasets imports 4** - `mistral.observability_datasets_imports.from_dataset` Populate the dataset with records from another dataset write - `mistral.observability_datasets_imports.from_file` Populate the dataset with records from an uploaded file write - `mistral.observability_datasets_imports.from_playground` Populate the dataset with records from playground conversations write - `mistral.observability_datasets_imports.from_spans` Populate the dataset with records mapped from telemetry spans write **Prompts versions 4** - `mistral.prompts_versions.create` CreatePromptVersion write - `mistral.prompts_versions.get` GetPromptVersion read - `mistral.prompts_versions.list` ListPromptVersions read - `mistral.prompts_versions.update` UpdatePromptVersionMetadata write **Skills versions 4** - `mistral.skills_versions.create` CreateSkillVersion write - `mistral.skills_versions.get` GetSkillVersion read - `mistral.skills_versions.list` ListSkillVersions read - `mistral.skills_versions.update` UpdateSkillVersionMetadata write **Admin API keys 3** - `mistral.admin_api_keys.create` Create Api Key destructive - `mistral.admin_api_keys.delete` Delete Api Key destructive - `mistral.admin_api_keys.list` Get Api Keys read **Admin user groups members 3** - `mistral.admin_user_groups_members.add` Assign Users To Group write - `mistral.admin_user_groups_members.list` Get User Group Members read - `mistral.admin_user_groups_members.remove` Remove Users From Group destructive **Admin user invites 3** - `mistral.admin_user_invites.create` Invite Users write - `mistral.admin_user_invites.delete` Delete Invite destructive - `mistral.admin_user_invites.list` Get Invite read **Agents aliases 3** - `mistral.agents_aliases.delete` Delete an agent version alias. destructive - `mistral.agents_aliases.list` List all aliases for an agent. read - `mistral.agents_aliases.update` Create or update an agent version alias. write Connectors credentials **3** Files **3** Fine tuning models **3** Libraries share **3** Models **3** Observability spans evaluations **3** Observability traces **3** Rag deployments **3** Workflows registrations **3** Admin scim sync **2** Admin spend limit **2** Admin usage **2** Admin user groups nested **2** Agents versions **2** Connectors organization share **2** Connectors share **2** Connectors tools **2** Connectors user credentials **2** Observability datasets records **2** Observability datasets tasks **2** Observability evaluation runs V2 **2** Observability evaluation runs V2 records **2** Observability evaluation runs V2 statistics **2** Observability optimizations **2** Observability projects **2** Observability spans **2** Observability traces spans **2** Rag ingestion pipeline configurations **2** Rag managed indexes documents **2** Service accounts roles **2** Workflows runs **2** Admin analytics vibe code usage by organization **1** Admin analytics vibe code usage by workspace **1** Admin analytics vibe work usage by agent stats **1** Admin analytics vibe work usage by time stats **1** Admin analytics vibe work usage by user stats **1** Admin audit logs **1** Admin rate limit **1** Admin roles **1** Admin user groups organization role **1** Admin workspaces users **1** Agents completions **1** Agents pages **1** Agents version **1** Audio speech **1** Audio voices V2 **1** Chat classifications **1** Chat completions **1** Chat moderations **1** Classifications **1** Connectors auth URL **1** Connectors authentication methods **1** Connectors organization credentials **1** Connectors workspace credentials **1** Conversations history **1** Conversations messages **1** Embeddings **1** Files URL **1** Fim completions **1** Libraries documents extracted text signed URL **1** Libraries documents signed URL **1** Libraries documents status **1** Libraries documents text content **1** Moderations **1** Observability dataset records payload **1** Observability dataset records properties **1** Observability evaluations V2 **1** Observability evaluations V2 runs **1** Observability logs **1** Observability logs fields **1** Observability logs fields options **1** Observability optimizations trials **1** Observability pipeline results **1** Observability projects evaluations V2 **1** Observability spans evaluations fields **1** Observability spans evaluations fields options **1** Observability spans fields **1** Observability spans fields options **1** Observability traces fields **1** Observability traces fields options **1** Ocr **1** Rag deployments metrics **1** Rag ingestion pipeline configurations run info **1** Rag managed indexes chunks **1** Realtime client sessions **1** Service accounts assignable roles **1** Users me **1** Users me organizations **1** Users me workspaces **1** Whoami **1** Workflows deployments logs **1** Workflows deployments workers **1** Workflows events **1** Workflows executions history **1** Workflows executions logs **1** Workflows executions trace events **1** Workflows executions trace info **1** Workflows executions trace otel **1** Workflows executions trace summary **1** Workflows metrics **1** Workflows runs history **1** This index shows a sample of each area. All 306 actions, with their inputs and prices, are in the [catalogue](https://actionlake.com/console/catalogue), which a free sandbox key can search. Questions ## The Mistral AI MCP server, answered. **Is there a Mistral AI MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 306 Mistral AI actions across rag managed indexes, workflows deployments, workflows executions and workflows, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Mistral AI. **What do I need to connect Mistral AI?** Mistral API key (console.mistral.ai > API Keys). The free call account { op: "connections.requirements", service: "mistral" } lists exactly what to paste. **Can an AI agent delete or change things in Mistral AI?** Only if its key allows it, and only with an explicit confirmation. 46 Mistral AI actions are destructive, including delete User, delete User Group and create Api Key. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Mistral AI API limit?** actionlake paces every call to the limits in the Mistral AI service file: 60 calls a minute per connection. Repeated reads are answered from cache (122 Mistral AI actions can be), which never reaches Mistral AI. **What does a Mistral AI action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (69 Mistral AI actions page). Cache hits, searches, dry runs and calls Mistral AI refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Mistral AI API does it cover?** The Mistral AI API 1.0.0 at api.mistral.ai. It is built from Mistral AI's documentation as read on 23 October 2026. 306 actions in 131 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Mistral AI data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Mistral AI credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Mistral AI Shares the most action names with - [OpenAI Admin 27](https://actionlake.com/connectors/openai-admin) - [Claude Admin (Anthropic) 24](https://actionlake.com/connectors/anthropic-admin-api) - [OpenRouter 21](https://actionlake.com/connectors/openrouter) - [Hugging Face 17](https://actionlake.com/connectors/hugging-face) - [Groq 10](https://actionlake.com/connectors/groq) - [xAI Grok API 10](https://actionlake.com/connectors/xai-grok-api) Joins with, on shared entities - [Adobe Frame.io (V4) 5](https://actionlake.com/connectors/adobe-frame-io-v4) - [Rubrik Security Cloud 4](https://actionlake.com/connectors/rubrik-security-cloud) - [Gitea 4](https://actionlake.com/connectors/gitea) - [Forgejo 4](https://actionlake.com/connectors/forgejo) - [Unleash 4](https://actionlake.com/connectors/unleash) - [Toggl Track 4](https://actionlake.com/connectors/toggl-track) Browse - [All AI connectors](https://actionlake.com/connectors/category/ai) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Mistral AI; the name is the vendor's own. Counts are from the Mistral AI service file, version 1.0.0. ## Give your agent Mistral AI today. [Connect Mistral AI free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/mistral-ai More: https://actionlake.com/llms.txt