How do I use AI Context Manager?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AI Context Manager sync the latest assets from the cloud" 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.

AI Context Manager

by dannybombastic

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

AI Context Manager MCP

Servidor MCP (Model Context Protocol) en Python que actúa como sync agent entre el workspace local y la aplicación cloud.

¿Qué hace?

Gestiona la carpeta .ai/ en tu workspace (skills, prompts, specs, contexto, bootstrap)
Sincroniza assets con la app cloud (cloud_sync pull/push)
Genera MODEL_BOOTSTRAP.md adaptado al entorno (vscode, claude, opencode, cli, generic)
Mantiene .gitignore actualizado para no commitear el contexto local

Related MCP server: Dev Tool Config Sync MCP Server

Requisitos

Python 3.11+
pip / pipx

Instalación

# Con pipx (recomendado, instala en entorno aislado)
pipx install .

# O con pip en un virtualenv
python -m venv .venv
source .venv/bin/activate   # Linux/macOS
.venv\Scripts\activate      # Windows
pip install -e .

Variables de entorno (obligatorias para sync cloud)

# Linux/macOS
export AI_CONTEXT_MANAGER_BASE_URL="https://cloud.example.com"
export AI_CONTEXT_MANAGER_TOKEN="pat_xxx"

# Windows (PowerShell)
$env:AI_CONTEXT_MANAGER_BASE_URL="https://cloud.example.com"
$env:AI_CONTEXT_MANAGER_TOKEN="pat_xxx"

# Windows (cmd)
set AI_CONTEXT_MANAGER_BASE_URL=https://cloud.example.com
set AI_CONTEXT_MANAGER_TOKEN=pat_xxx

Arrancar el servidor MCP

# Modo stdio (para clientes MCP como Claude Desktop, OpenCode, etc.)
python -m mcp_server

# O usando el script instalado
ai-context-manager serve

Configuración en VS Code (tasks.json)

Crear .vscode/tasks.json en tu proyecto:

{
  "version": "2.0.0",
  "tasks": [
    {
      "label": "AI Context Manager: Start MCP",
      "type": "shell",
      "command": "python -m mcp_server",
      "options": {
        "env": {
          "AI_CONTEXT_MANAGER_BASE_URL": "https://cloud.example.com",
          "AI_CONTEXT_MANAGER_TOKEN": "pat_xxx"
        }
      },
      "problemMatcher": []
    },
    {
      "label": "AI Context Manager: Sync (pull)",
      "type": "shell",
      "command": "ai-context-manager cloud-sync --direction pull",
      "options": {
        "env": {
          "AI_CONTEXT_MANAGER_BASE_URL": "https://cloud.example.com",
          "AI_CONTEXT_MANAGER_TOKEN": "pat_xxx"
        }
      },
      "problemMatcher": []
    }
  ]
}

Configuración en Claude Desktop

Añadir en claude_desktop_config.json:

{
  "mcpServers": {
    "ai-context-manager": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "env": {
        "AI_CONTEXT_MANAGER_BASE_URL": "https://cloud.example.com",
        "AI_CONTEXT_MANAGER_TOKEN": "pat_xxx"
      }
    }
  }
}

Configuración en OpenCode

Añadir en tu config de OpenCode:

{
  "mcp": {
    "servers": {
      "ai-context-manager": {
        "command": "python",
        "args": ["-m", "mcp_server"],
        "env": {
          "AI_CONTEXT_MANAGER_BASE_URL": "https://cloud.example.com",
          "AI_CONTEXT_MANAGER_TOKEN": "pat_xxx"
        }
      }
    }
  }
}

Setup inicial de un proyecto

# 1. Inicializar .ai/ en el workspace
ai-context-manager init --mode workspace

# 2. Vincular con proyecto cloud
ai-context-manager cloud-link --project-key my-project

# 3. Descargar assets del cloud
ai-context-manager cloud-sync --direction pull

# 4. Asegurar .gitignore
ai-context-manager ensure-gitignore

Tools disponibles (MCP)

Tool	Descripción
`init_storage`	Inicializa `.ai/` en workspace o global
`ensure_gitignore`	Añade `.ai/` al `.gitignore`
`scan_repo`	Escanea el repo buscando assets IA
`list_assets`	Lista assets (skills/prompts/specs/context)
`register_asset`	Registra un asset existente en el registry
`move_asset`	Mueve un asset actualizando el registry
`remove_asset`	Elimina un asset del registry
`create_skill`	Crea un nuevo skill desde template
`create_prompt`	Crea un nuevo prompt desde template
`create_spec`	Crea una nueva spec desde template
`generate_bootstrap`	Genera `MODEL_BOOTSTRAP.md` para el entorno
`cloud_project_link`	Vincula workspace con proyecto cloud
`cloud_sync`	Sincroniza assets (pull: cloud→local, push: local→cloud)
`cloud_pull_backup`	Descarga un backup específico del cloud

Resources disponibles (MCP)

Resource	Descripción
`registry://`	Contenido completo del registry.json
`context://bootstrap`	Contenido del MODEL_BOOTSTRAP.md
`skills://<id>`	Contenido de un skill por ID
`prompts://<id>`	Contenido de un prompt por ID
`specs://<id>`	Contenido de una spec por ID

Estructura local generada

.ai/
  registry.json          # fuente de verdad local
  context/
    AI_GUIDELINES.md
    MODEL_BOOTSTRAP.md   # generado por generate_bootstrap
  skills/
    *.md
  prompts/
    *.md
  specs/
    *.md
  templates/
    skill.md
    prompt.md
    spec.md
  .sync/
    state.json           # estado de sync (hashes/ETags)
    project.json         # binding local_path <-> project_key

Available Tools

12 tools

ai_cloud_pullC

DEPRECATED: Descarga assets. Usa cloud API directamente para gestionar contexto.

Inputs: type, slug, workspace, overwrite, +2 more.

ai_cloud_pushB

Publica assets locales en StandarCloud. Sube skills, prompts y specs al servidor.

Inputs: type, slug, project_slug, workspace.

ai_cloud_statusA

Muestra el estado de sincronización: assets locales vs remotos, pendientes de push/pull.

Inputs: workspace.

ai_cloud_syncB

Sincroniza cloud → workspace en modo espejo (por defecto). Opcionalmente permite push local → cloud.

Inputs: workspace, dry_run, push.

ai_detect_environmentB

Detectar entorno actual (claude, vscode-copilot, opencode, unknown)

Inputs: no named parameters.

ai_materialize_documentsA

Materializar documentos nativos del entorno actual (Claude.md para Claude, .github/copilot-instructions.md para Copilot, etc.). Requiere token de API.

Inputs: documents (required).

ai_memory_addB

Añade una entrada de memoria a una sesión (taggeada: observation/recommendation/decision/architecture/other).

Inputs: session_id (required), content (required), tag, title, +1 more.

ai_memory_listC

Lista entradas de memoria (puede filtrar por session_id, project y/o tag).

Inputs: session_id, project, 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.

Inputs: project (required), session_id, external_id, workspace, +3 more.

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.

Inputs: project (required), external_id, title.

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.

Inputs: project_slug, workspace, description, force.

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.

Inputs: force.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.2/5.0

Scored 2026-06-03 20:55 across 12 tools

Disambiguation3/5

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.

Naming Consistency4/5

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.

Tool Count5/5

12 tools cover the domain of context management, cloud sync, memory, and environment setup without being overwhelming or sparse.

Completeness4/5

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.

Maintenance

ActivityNo data

ResponsivenessOutdated data

Resources

Related MCP Connectors

Fastio
io.fast
Give every project one workspace for its files, its team, and its AI agents.
Workplace & Productivity Project Management File Systems
1
https://mcp.fast.io/mcp/tools
FileaifyA
com.fileaify
Project memory, documentation and controlled secret access for AI coding agents.
Knowledge & Memory Documentation Access Security
431
https://fileaify.com/mcp
Aurentia
fr.aurentia
Your Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client.
CRM Project Management Workplace & Productivity
1
https://entrepreneurs.aurentia.fr/api/mcp/aurentia
Shardflux
dev.shardflux
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Agent Orchestration Code Execution Command Line
1
https://mcp.shardflux.dev/mcp

Related MCP Servers

Mnehmos Synch
Knowledge & Memory Autonomous Agents Developer Tools
Mnehmos
A
license
Not graded
quality
D
maintenance
Provides persistent context synchronization and memory management for AI agents across sessions and projects, including file indexing, bug tracking, spatial navigation, and agent-to-agent handoff coordination.
Updated 10 months ago (2026-01-10 22:35 UTC)
9 npm
3
MIT
Dev Tool Config Sync MCP
Developer Tools Version Control
akurinnoy
A
license
Not graded
quality
D
maintenance
Syncs and manages configurations for dev tools like Claude Code and Gemini CLI across workspaces with snapshot history and rollback capabilities.
Updated 4 months ago (2026-07-04 17:14 UTC)
Eclipse Public 2.0
gcontext-mcp
Cloud Storage Command Line Developer Tools
bleak-ai
A
license
Not graded
quality
F
maintenance
Bridges AI agents to a gcontext workspace in the cloud, enabling file and folder management while keeping secret values and script execution local.
Updated 4 months ago (2026-07-14 15:41 UTC)
MIT
skills-manager-mcp
Developer Tools Agent Orchestration
AbdulqaderAhmed
F
license
A
quality
B
maintenance
Acts as a personal AI development environment manager, enabling workspace bootstrapping, headless skill and bundle installation, global caching, and health diagnostics.
Updated 24 days ago (2026-10-20 07:28 UTC)
7
27 npm
-