Mistral Agent Manager
Provides a FastAPI web server interface for managing Mistral AI agents through REST API endpoints
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mistral Agent Managercreate a new agent for customer support"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
đ FastAPI Server - Mistral Agent Manager
Ce dossier contient le serveur FastAPI pour la gestion des agents Mistral via API REST.
đ Structure
mcp-server/
âââ main.py # Serveur FastAPI principal
âââ simple_server.py # Serveur MCP simple (stdio) - ancien
âââ test_mcp.py # Tests du serveur MCP - ancien
âââ pyproject.toml # Configuration du projet
âââ uv.lock # Lock file des dĂ©pendances
âââ .env # Variables d'environnement
âââ .python-version # Version Python
âââ .gitignore # Fichiers Ă ignorer
âââ .venv/ # Environnement virtuel PythonRelated MCP server: Azure AI Foundry Agent MCP
đ DĂ©marrage rapide
Installer uv (si pas déjà fait) :
curl -LsSf https://astral.sh/uv/install.sh | sh export PATH="$HOME/.local/bin:$PATH"Installer les dépendances :
cd mcp-server uv sync --lockedDémarrer le serveur MCP :
uv run python main.py
đ§ Utilisation avec l'inspecteur MCP
Lancer l'inspecteur :
npx @modelcontextprotocol/inspectorSe connecter au serveur :
Transport :
stdioCommand :
uv run python main.pyWorking Directory :
/Users/yoandicosmo/Documents/LeChat MCP Hack/mcp-server
Accéder à l'interface :
MCP Inspector : http://localhost:6274 (quand l'inspecteur est lancé)
đ ïž Outils disponibles
â
create_agent- CrĂ©er un nouvel agent Mistralâ
list_agents- Lister tous les agentsâ
get_agent_details- Obtenir les dĂ©tails d'un agentâ
delete_agent- Supprimer un agent par IDâ
search_agent- Rechercher un agent par nom
đ§ Configuration
Variables d'environnement : Configurez
MISTRAL_API_KEYdans.envTransport : Le serveur utilise stdio pour la communication MCP
API Mistral : Intégration complÚte avec l'API Mistral
đ IntĂ©gration avec Le Chat
Pour utiliser ce serveur MCP avec Le Chat :
Configurer Le Chat pour pointer vers ce serveur MCP
Utiliser les outils directement dans Le Chat pour gérer les agents Mistral
Créer des agents via des prompts naturels dans Le Chat
đ Documentation
MCP Inspector : http://localhost:6274 (quand l'inspecteur est lancé)
Documentation MCP : https://modelcontextprotocol.io/
This server cannot be deployed
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
MCP facade over the Nebelus Construction API. ~48 tools give full agent build parity: create/update/probe agents, edit graphs, attach knowledge and vector stores, wire connectors, set governance policies and locked guardrails, enable grounding-trace, and read deployment wiring. Purpose-built for regulated industries: data residency is enforced per region (EU / GCC-KSA), with PII controls and an audit trail. Agents are created as drafts â no deploy tool is exposed over MCP by design; publishing happens in the Nebelus console.
AI agent registry â search, discover, register, and connect agents via MCP.
Let AI agents query data and act across all your business apps via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables MCP-compatible clients to interact with deployed Agent5ive agents as tools. Allows users to query agent purposes and send messages to leverage Agent5ive capabilities through natural language.28 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Azure AI Agent Service by automatically discovering agents and creating MCP tools for querying and managing agent workflows.1MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to read and modify Mendix application models through MCP tools for creating modules, entities, pages, microflows, deploying, and querying runtime data.1-
- AlicenseNot gradedqualityCmaintenanceEnables managing OpAMP agents via natural language, allowing listing agents, viewing details, and setting or deleting configuration overrides.MIT