Chat with Mistral's frontier models, embed text, fill in code with Codestral, and manage fine-tuning jobs to train custom models on your data.
Use with AI AssistantsMCP
Connect Claude, Cursor, or any MCP-compatible client — then call tools directly
① Add This MCP Server
Paste into your AI client config — then all its tools are available instantly.
{
"mcpServers": {
"mistral": {
"url": "https://mcp.aerostack.dev/s/aerostack/mcp-mistral",
"headers": {
"Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
}
}
}
}Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.
② Call a Tool
Ask your AI assistant to call a specific tool, or send raw JSON-RPC:
Natural Language Prompt
“Use the _ping tool to verify mistral credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”
Using a Workspace?
Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.
Chat with Mistral's frontier models, embed text, fill in code with Codestral, and manage fine-tuning jobs to train custom models on your data.
Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-mistral
This MCP server gives AI agents access to Mistral via 12 tools. Connect it to any Aerostack workspace and your agents can interact with Mistral directly.
| Tool | Description |
|---|---|
chat | Send messages to a Mistral model and receive a response. Supports multi-turn conversations, system prompts, and JSON mode |
embed | Generate text embeddings using Mistral Embed model for semantic search and similarity tasks |
fill_in_middle | Fill in the middle of code using Codestral — provide prefix and suffix code, get completion |
list_models | List all available Mistral models including fine-tuned and base models |
get_model | Get details about a specific Mistral model by its ID |
upload_file | Upload a file to Mistral for use in fine-tuning jobs. Returns a file ID |
list_files | List all uploaded files in your Mistral account |
delete_file | Delete an uploaded file from your Mistral account |
create_fine_tuning_job | Create a fine-tuning job to train a custom Mistral model on your data |
list_fine_tuning_jobs | List all fine-tuning jobs with their status, model, and created date |
get_fine_tuning_job | Get details and current status of a specific fine-tuning job |
cancel_fine_tuning_job | Cancel a running fine-tuning job |
| Variable | Required | Description |
|---|---|---|
MISTRAL_API_KEY | Yes | Your Mistral API key — found at console.mistral.ai/api-keys |
Add the following secrets under Project → Secrets:
MISTRAL_API_KEYOnce added, every AI agent in your workspace can use Mistral tools automatically.
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-mistral \
-H 'Content-Type: application/json' \
-H 'X-Mcp-Secret-MISTRAL-API-KEY: your-mistral-api-key' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"chat","arguments":{}}}'
MIT
Live Endpoint
https://mcp.aerostack.dev/s/aerostack/mcp-mistral
Sub-50ms globally · Zero cold start
@aerostack
Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.
by @aerostack
Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP
by @aerostack
Conversations, contacts, tickets, articles via Intercom's official MCP
by @aerostack
Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.
by @aerostack
Deployments, projects, domains, env vars, logs via Vercel's official MCP
by @aerostack
Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.
by @aerostack
Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.
Yes. The Mistral MCP includes a create_fine_tuning tool that lets Claude create fine tunings in your Mistral account from a plain-English prompt. You can also update and delete fine tunings — no Mistral UI needed.
Yes. The Mistral MCP includes tools to list and retrieve models from your Mistral account. Claude can filter, sort, and summarize models based on your instructions.
Yes. The Mistral MCP uses the open Model Context Protocol standard, so it works in Claude, Cursor, Windsurf, and any other MCP-compatible AI tool. All 12 Mistral tools are available everywhere you connect it — install once on Aerostack.
Yes. Aerostack hosts the Mistral MCP with encrypted credential storage and per-account authentication. Your Mistral credentials are never shared with Claude's conversation — they're used server-side only.