No install? Use cloud.anythingmcp.com directly.
Sign in, install the Todoist in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Todoist (personal/team task manager) from any AI agent: projects, tasks, comments, labels, sections. 12 tools, Bearer token auth, REST API v2.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Todoist, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Todoist + Gemini
Drive Todoist (personal/team task manager) from any AI agent: projects, tasks, comments, labels, sections. 12 tools, Bearer token auth, REST API v2.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
TODOIST_API_TOKEN
Paso 1 — Obtener credenciales
Setup:
- Sign in to https://todoist.com → top-right avatar → Settings → Integrations → Developer → API token → Copy.
- Set
TODOIST_API_TOKENto it.
Authentication: Authorization: Bearer ${TODOIST_API_TOKEN}. The token is per-user; everything done with it appears as that user's actions. Personal API tokens never expire.
Hierarchy: Project → Section (optional) → Task → Sub-task. Tasks can also live directly in a project without a section. The Inbox is a special project (inbox_project=true).
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —Todoistdebería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
todoist_get_projects | List all projects the user can access |
todoist_create_project | Create a new project |
todoist_get_active_tasks | List active (non-completed) tasks with filters |
todoist_get_task | Fetch a single task by ID |
todoist_create_task | Create a task |
todoist_update_task | Update a task |
todoist_complete_task | Mark a task as completed |
todoist_reopen_task | Reopen a previously-completed task |
todoist_delete_task | Permanently delete a task |
todoist_get_comments | List comments on a project OR a task |
todoist_create_comment | Add a comment to a project or task |
todoist_get_labels | List the user's personal labels |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?