AI Context Manager
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_CONTEXT_MANAGER_TOKEN | Yes | API token for authentication with the cloud service | |
| AI_CONTEXT_MANAGER_BASE_URL | Yes | Base URL of the cloud application |
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
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai_standard_initA | Inicializa el workspace con el directorio .acm/ y lo vincula a un proyecto de StandarCloud. Si no se especifica project_slug, lista los proyectos disponibles y guía al usuario. Si se especifica project_slug, crea la estructura .acm/ y escribe project.json. |
| ai_detect_environmentB | Detectar entorno actual (claude, vscode-copilot, opencode, unknown) |
| ai_materialize_documentsA | Materializar documentos nativos del entorno actual (Claude.md para Claude, .github/copilot-instructions.md para Copilot, etc.). Requiere token de API. |
| ai_sync_environment_docsB | Sincronizar documentos nativos desde la nube para el entorno actual. Detecta el entorno, obtiene documentos de la API y los materializa localmente. |
| ai_cloud_pushB | Publica assets locales en StandarCloud. Sube skills, prompts y specs al servidor. |
| ai_cloud_pullC | DEPRECATED: Descarga assets. Usa cloud API directamente para gestionar contexto. |
| ai_cloud_syncB | Sincroniza cloud → workspace en modo espejo (por defecto). Opcionalmente permite push local → cloud. |
| ai_cloud_statusA | Muestra el estado de sincronización: assets locales vs remotos, pendientes de push/pull. |
| ai_session_ensureA | Crea o reutiliza una Session en el backend cloud (Django), asociada a un Project. Si existe una sesión con el mismo external_id para ese project, retorna la primera. |
| ai_memory_addB | Añade una entrada de memoria a una sesión (taggeada: observation/recommendation/decision/architecture/other). |
| ai_memory_listC | Lista entradas de memoria (puede filtrar por session_id, project y/o tag). |
| ai_memory_materialize_historyB | Trae histórico de sesión desde la web (Django) y lo materializa como prompt file nativo del entorno de chat (vscode-copilot, claude) o como export JSON nativo de OpenCode. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Route Library | Biblioteca de rutas oficiales y best_effort por entorno |
| Official Docs | Biblioteca de documentación oficial por entorno |
TDQS
Scored across 12 tools
Most tools are distinct, but ai_cloud_push and ai_cloud_sync (with push option) overlap, and ai_materialize_documents and ai_sync_environment_docs are very similar. The deprecated ai_cloud_pull adds confusion.
All tools use 'ai_' prefix and underscore separation, with a mix of verb_first and noun_first patterns (e.g., detect_environment vs cloud_push). Overall readable and fairly consistent, but not perfectly uniform.
12 tools cover the domain of context management, cloud sync, memory, and environment setup without being overwhelming or sparse.
Core workflows (init, sync, memory, session, environment detection) are covered. Minor gaps like memory deletion or cloud asset management are absent but not critical for the stated purpose.