Canvas MCP Server

What is Canvas MCP Server?

A Model Context Protocol (MCP) server implementation for the Canvas LMS API. It provides tools to interact with Canvas programmatically, such as listing courses with optional enrollment type filtering, and integrates with the Cursor client for AI-assisted workflows.

How to use Canvas MCP Server?

Install dependencies (npm install), set environment variables CANVAS_BASE_URL and CANVAS_ACCESS_TOKEN, build (npm run build), and start (npm start). Then configure the server in Cursor’s MCP settings using the provided JSON snippet and restart Cursor to access the tools.

Key features of Canvas MCP Server

• Lists courses from Canvas LMS with optional enrollment type filtering
• Interactive help prompt (list-courses-help) for tool usage guidance
• Built with TypeScript and the MCP SDK
• Integrates directly with the Cursor client as an MCP server
• Easy setup via environment variables and npm scripts

Use cases of Canvas MCP Server

• Quickly retrieve a list of Canvas courses in a development or AI-assisted environment
• Filter courses by enrollment type (teacher, student, ta) for targeted queries
• Integrate Canvas data into an agentic workflow using Cursor’s MCP tools panel
• Extend functionality by adding new API methods and tools through the provided SDK