Home
Resources

MCP

The Mistral MCP server connects an AI agent to your Studio workspace over the Model Context Protocol. It exposes your workspace as MCP tools and authenticates each request with your Mistral API key.

Use it from wherever your agent runs: a coding CLI, an IDE, a desktop assistant, or your own application.

Endpointhttps://api.mistral.ai/mcp
TransportStreamable HTTP
AuthenticationAuthorization: Bearer <MISTRAL_API_KEY>
Before you begin

Before you begin

  • A Mistral API key. Keys are workspace-scoped, so the agent gets the access that key already has.
  • An MCP client that supports the streamable HTTP transport and static request headers.

Export the key in the environment that launches your client:

export MISTRAL_API_KEY="your_api_key"
Connect a client

Connect a client

vibe mcp add mistralai \
  --url https://api.mistral.ai/mcp \
  --transport streamable-http \
  --api-key-env MISTRAL_API_KEY

This writes the entry to ~/.vibe/config.toml:

[[mcp_servers]]
name = "mistralai"
transport = "streamable-http"
url = "https://api.mistral.ai/mcp"

[mcp_servers.auth]
type = "static"
api_key_env = "MISTRAL_API_KEY"

The configuration stores the variable name and the environment holds the key. Run /mcp mistralai in a session to list the tools. See MCP servers for permissions and tool filtering.

What the server exposes

What the server exposes

The server groups its tools by Studio capability.

CapabilityWhat an agent can do
AppsList your apps, read an app's modules, environments, and running versions, read deploy runs and module or gateway logs, redeploy or roll back a module to a version it already ran, and publish or unpublish an app in the catalog. Env var values are never returned, only their names.
ConnectorsList your connectors, read their details and the tools each one exposes, list their credentials, and link to the Studio page that adds a connector. Secret values are never returned.
DocumentationSearch docs.mistral.ai and read its pages as Markdown.
EvaluationsManage evaluation projects and evaluations, read runs and records, and follow optimizations.
LibrariesList, create, and delete document libraries, add or remove documents, and manage who can access a library. Document contents are never returned.
ObservabilitySearch traces, spans, and logs from your applications, and open a single trace or span.
OrganizationIdentify your user, organization, and workspace, look up workspace members, and resolve a name to a user ID.
PromptsList prompts, read a version by number or alias, and write a new version.
SecretsList secrets, read a secret's metadata and versions, delete a secret or some of its versions, and restore a deleted version. Secret values are never returned.
SkillsBrowse the same Skill catalog as Studio, read a Skill and its files, write a new version, change sharing, or delete a Skill.
WorkflowsList workflows, deploy managed workflows, start and signal executions, read events and logs, and manage schedules.

Apps, Evaluations, Observability, and Secrets tools appear only for workspaces where those features are turned on. The server lists the tools available to your key, so ask your client for its tool list, or call tools/list. Each tool describes its own arguments.

Access and permissions

Access and permissions

Every call uses your API key's permissions.

Some tools write or delete. Configure per-tool approval in your client to review those calls before they run.

Troubleshooting

Troubleshooting

ProblemCauseSolution
401 {"detail":"Invalid API Key"}The key is missing, misspelled, or revoked.Export the variable in the environment that launches your client, and check the key is active in the console.
A tool call returns a permission error.The operation requires additional workspace access.Ask a workspace admin for the matching access, then retry.
Apps, Evaluations, Observability, or Secrets tools are missing from the tool list.The feature is off for your workspace.Check that the feature is available in Studio, then reconnect the client.
Next steps

Next steps