Canvas MCP Server

MCP server for Canvas LMS with up to 101 tools and 8 agent skills. Designed for Claude Desktop, Cursor, Codex, Windsurf, and 40+ other agents; setup and capabilities vary by client.

Quick Start

1. Install the MCP server (everything else, including the skills, needs it running):

• Claude Desktop: download canvas-mcp.mcpb from the latest release and double-click it. It prompts for your Canvas URL and token; no terminal needed. Details.
• Cursor, Zed, Windsurf, Continue, Claude Code and other clients: pip install into a virtualenv, add your token to .env, and point your client at the canvas-mcp-server binary. Local Installation has the per-client config blocks.

2. Verify: canvas-mcp-server --test should report a successful Canvas connection. Then restart your client.

3. Optional: add the workflow skills. These teach your agent the multi-step recipes (weekly plan, morning check, bulk grading, peer review, course QC) on top of the tools:

npx skills add vishalsachdev/canvas-mcp

See Agent Skills for the list. If your agent is Claude Code, the same recipes are also available as slash commands.

For AI Agents

Canvas MCP provides up to 101 tools for interacting with Canvas LMS; the default profile registers fewer, and optional feature-gated tools can raise the total to 101. Tools are organized by user type:

Quick Reference

Course identifiers: Canvas ID (12345), course code (badm_350_120251_246794), or SIS ID

Cannot do: Create/delete courses, modify course settings, access other users' data

Rate limits: ~700 requests/10 min. Use max_concurrent=5 for bulk operations.

Full documentation: AGENTS.md | tools/TOOL_MANIFEST.json | tools/README.md

Overview

The Canvas MCP Server bridges the gap between AI assistants and Canvas Learning Management System, providing role-specific workflows for students, educators, learning designers, and developers. Built on the Model Context Protocol (MCP), it is designed for MCP-compatible clients; setup and supported capabilities vary by client.

Latest Release: v1.12.0

Released: August 2026 | Full Changelog | All Releases

A safety release: every delete tool now asks first. Four changes are breaking. Each one's migration is a line long:

• delete_announcement removed → call delete_announcement_with_confirmation with the same arguments; it previews first, then deletes on the second call with the token (#318)
• dry_run removed from the three announcement delete tools → drop the argument; a call without confirmation_token is the dry run and deletes nothing. bulk_delete_announcements used to delete on the first call; it previews now (#318)
• confirmation_token required on all seven delete tools (delete_announcement_with_confirmation, bulk_delete_announcements, delete_announcements_by_criteria, delete_page, delete_module, delete_module_item, delete_assignment_with_confirmation) → call once with your normal arguments, show the preview, then call again with identical arguments plus the token from the Confirmation token: line. Tokens are single-use, expire in 5 minutes, and stop matching if the target or the arguments changed (#318). Thanks @zqian for the request
• Python 3.10 dropped → requires-python >= 3.11; upgrade the interpreter, or pin canvas-mcp<1.12 until you can (#315)

Also new: delete_assignment_with_confirmation (preview shows due date, points and whether submissions exist); ACCESSIBILITY_CHECKERS so institutions without UDOIT/UFIXIT can set none and drop the three UFIXIT tools while keeping the built-in scanner (#325, thanks @jonespm); the content migration tools (#309); and a Skill Request issue template (#302)