llms.txt@docs · git:20260819.f6fb9f5 · 2026-08-19 · sha256 f8b43046d6b3c38f
llms.txt@docs git:20260819.f6fb9f5A
Immutable. This exact content is served forever at /api/v1/blob/f8b43046d6b3c38f.
# Canvas MCP > Canvas MCP is an open-source Model Context Protocol (MCP) server that bridges AI assistants with Canvas Learning Management System (LMS). It provides 99 tools for students, educators, and developers to interact with Canvas using natural language. It is designed for MCP-compatible clients and includes optional privacy controls for FERPA-conscious workflows. Canvas MCP enables AI assistants to query courses, assignments, grades, discussions, and more through the Canvas API. Its code execution API can process bulk operations locally without loading every item into the model's context. ## Key Features - Natural language interface for Canvas LMS - 99 MCP tools for comprehensive Canvas integration - 8 reusable agent skills (workflow recipes) installable into 40+ agents via skills.sh - Optional student identity anonymization - Code execution API for bulk grading and operations - Works with Claude, ChatGPT (via MCP plugins), Cursor, Zed, Windsurf, and other MCP clients ## Documentation - [Home](https://canvas-mcp.illinihunt.org/): Main project website with features and installation - [Student Guide](https://canvas-mcp.illinihunt.org/student-guide.html): How students can use Canvas MCP for tracking assignments, grades, and deadlines - [Educator Guide](https://canvas-mcp.illinihunt.org/educator-guide.html): How educators can use Canvas MCP for course management and analytics - [Learning Designer Guide](https://canvas-mcp.illinihunt.org/learning-designer-guide.html): Course structure audits, accessibility scanning, and module building - [Code API / Bulk Grading](https://canvas-mcp.illinihunt.org/bulk-grading.html): Developer documentation for the code execution API ## Source Code - [GitHub Repository](https://github.com/vishalsachdev/canvas-mcp): Full source code, issues, and contributions - [PyPI Package](https://pypi.org/project/canvas-mcp/): Python package installation via pip - [MCP Server Registry](https://github.com/modelcontextprotocol/servers): Listed in the official MCP server registry ## Tool Categories Canvas MCP provides tools in these categories: - Course Management: list_courses, get_course_details, get_course_content_overview - Assignments: list_assignments, get_assignment_details, create_assignment, update_assignment, bulk_grade_submissions - Discussions: list_discussion_topics, post_discussion_entry, reply_to_discussion_entry - Messaging: send_conversation, send_peer_review_inbox_messages - Analytics: get_student_analytics, get_assignment_analytics, get_peer_review_completion_analytics - Modules: list_modules, create_module, update_module, delete_module - Pages: list_pages, create_page, edit_page_content, get_page_content - Rubrics: list_rubrics, get_rubric, create_rubric, associate_rubric, grade_with_rubric - Student self-service: get_my_upcoming_assignments, get_my_course_grades, get_my_todo_items, get_my_peer_reviews_todo ## Use Cases - Students: "What assignments are due this week?" "What's my grade in CS 101?" - Educators: "Which students haven't submitted the midterm?" "Send reminders to students with incomplete peer reviews" - Developers: "Grade all notebook submissions that contain a specific function" ## Optional - [License](https://github.com/vishalsachdev/canvas-mcp/blob/main/LICENSE): MIT License - free for commercial and personal use - [Contributing](https://github.com/vishalsachdev/canvas-mcp/blob/main/CONTRIBUTING.md): How to contribute to the project