revision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEN_MODEL | No | Model to use for generation (optional). | |
| TRANSCRIBE_MODEL | No | Model to use for transcription (optional). | |
| REVISION_SAAS_URL | No | URL of the hosted instance to use SaaS mode. | |
| OPENROUTER_API_KEY | No | OpenRouter API key used by the local pipeline. | |
| REVISION_WORKSPACE | No | Workspace directory for local mode. | |
| REVISION_SAAS_TOKEN | No | Token for the hosted instance to use SaaS mode. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| liste_coursB | Liste les cours du dossier de travail local (id, titre, état). |
| creer_coursC | Crée un cours local (dossier de travail) à partir d'un titre. |
| deposer_fichierC | Copie un fichier local (audio m4a/mp3/wav, PDF de diapos…) dans les sources du cours. |
| lancer_generationA | Lance la chaîne transcription → plan → fiche/questions/cartes en arrière-plan.
|
| detail_coursB | État d'un cours local : artefacts produits, sources, et fin du journal de génération. |
| ficheB | Fiche markdown du cours local (aperçu 6000 caractères ; complet=True pour tout). |
| cartesC | Cartes de révision du cours local. Écrit le JSON complet dans |
| exporter_ankiC | Construit le deck Anki (.apkg) à partir des cartes du cours local. |
| telecharger_fichierC | Copie un artefact local (fiche.md, questions.json, cards.json, transcript.md, plan.json, export.apkg) vers |
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 9 tools
Most tools have distinct purposes: liste_cours lists all courses while detail_cours inspects one; fiche, cartes, and telecharger_fichier retrieve different artifact types; deposer_fichier uploads sources vs telecharger_fichier downloads outputs. Only slight conceptual overlap between detail_cours (status) and the artifact-retrieval tools (fiche/cartes), but descriptions clarify the split.
Most names follow a French verb_noun snake_case pattern (liste_cours, creer_cours, deposer_fichier, lancer_generation, detail_cours, exporter_anki, telecharger_fichier). The bare nouns 'fiche' and 'cartes' deviate, but the overall convention is clear and consistent.
Nine tools is well-scoped for a course-generation pipeline: course management, source deposit, generation, status, artifact retrieval, and export. Each tool earns its place with no redundancy.
The surface covers the full lifecycle: create/list courses, deposit sources, run generation, check status, retrieve fiche/cartes/transcript artifacts, and export to Anki. Missing delete/update operations (removing a course or source file) are minor gaps an agent could work around.