francestudent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FS_OUTPUT_DIR | No | Optional directory where generated images are saved. | |
| FS_SESSION_FILE | No | Optional path to the saved session file. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fs_generate_imageA | Génère une ou plusieurs images avec le modèle gpt-image-2-codex via ton compte France Student IA (discussion incognito avec un agent OpenAI). Les PNG sont enregistrés sur le disque et renvoyés. Chaque image prend ~20-30 s et consomme du budget de chat France Student. |
| fs_usageB | Affiche le budget de chat et les limites de débit restants sur ton compte France Student. |
| fs_list_agentsA | Liste les agents (modèles) disponibles sur ton compte. Seuls les agents OpenAI savent générer des images. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools target clearly separate actions: generating images, checking account usage, and listing available agents. There is no meaningful overlap that would cause an agent to misselect.
All tools share the fs_ prefix, but the suffixes mix verb-noun patterns with a noun-only form: fs_generate_image and fs_list_agents are action-oriented, while fs_usage is not. The pattern is still readable and mostly consistent.
Three tools is a well-scoped surface for a focused image-generation/account service. Each tool clearly earns its place without unnecessary bloat.
The set covers image generation, budget/rate-limit inspection, and agent discovery, which are the core operations implied by the server. Minor gaps exist, such as no tool to inspect or manage previously generated images, but core workflows are covered.