Canvas MCP Server
Connects Claude Desktop to Canvas LMS to monitor academic activities like assignments, announcements, and upcoming deadlines. It enables users to track courses and pending tasks through a unified interface using the Canvas REST API.
README
Canvas MCP Server
MCP Server que conecta Claude Desktop con Canvas LMS, permitiendo monitorear tareas, entregas, anuncios y pendientes académicos directamente desde Claude.
Tools disponibles
| Tool | Descripción |
|---|---|
courses |
Materias activas del semestre |
assignments(course_id) |
Tareas con fecha límite |
announcements(course_id) |
Anuncios de profesores |
upcoming |
Todo lo que vence pronto (vista unificada) |
todo |
Pendientes sin entregar |
Requisitos
- Python 3.12+
- Token de API de Canvas LMS
- Docker y Docker Compose (opcional, para deploy)
Instalación local
# Clonar el repositorio
git clone https://github.com/tu-usuario/canvas-mcp.git
cd canvas-mcp
# Crear entorno virtual e instalar dependencias
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
# Configurar variables de entorno
cp .env.example .env
# Editar .env con tu token de Canvas y configuración
Configuración
Edita el archivo .env con tus datos:
CANVAS_BASE_URL=https://tu-instancia-canvas.edu
CANVAS_TOKEN=tu_token_de_canvas
MCP_HOST=127.0.0.1
MCP_PORT=8000
MCP_SECRET=tu_secreto_para_autenticar
Obtener el token de Canvas
- Inicia sesión en tu Canvas LMS
- Ve a Cuenta → Configuración
- En la sección Tokens de acceso aprobados, clic en + Nuevo token de acceso
- Copia el token generado y pégalo en
CANVAS_TOKEN
Uso
Ejecutar localmente
source .venv/bin/activate
python main.py
El server arranca en http://localhost:8000/sse.
Ejecutar con Docker
docker compose up -d
Para ver los logs:
docker compose logs -f
Para detener:
docker compose down
Conectar con Claude Desktop
Agrega esto a tu claude_desktop_config.json:
Local:
{
"mcpServers": {
"canvas": {
"type": "sse",
"url": "http://localhost:8000/sse"
}
}
}
Remoto (con tunnel o VPS):
{
"mcpServers": {
"canvas": {
"type": "sse",
"url": "https://tu-dominio.com/sse",
"headers": {
"Authorization": "Bearer TU_MCP_SECRET"
}
}
}
}
La ubicación del archivo de configuración:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Deploy en VPS
# En el servidor
git clone https://github.com/tu-usuario/canvas-mcp.git
cd canvas-mcp
cp .env.example .env
# Editar .env con los valores reales
docker compose up -d
Stack
- Python + FastMCP + httpx + python-dotenv
- Transporte: SSE (Server-Sent Events)
- Canvas API: REST v1 con Bearer Token
Licencia
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.