Canvas API MCP

Overview

Canvas API MCP is a Model Context Protocol (MCP) server: MCP server exposing the Canvas LMS REST API (1,116 endpoints) for AI assistants. Because it speaks the Model Context Protocol, AI assistants can use Canvas API MCP as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package canvas-api-mcp (via uvx) speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need CANVAS_BASE_URL, CANVAS_TOKEN. The current release is v1.1.0, published under the MIT license, with source at JohannsenLum/canvas-api-mcp on GitHub.

On mcp.site, Canvas API MCP sits in the Design category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Canvas API MCP for JohannsenLum, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "canvas_api_mcp": {
      "command": "uvx",
      "args": [
        "canvas-api-mcp"
      ],
      "env": {
        "CANVAS_BASE_URL": "<canvas-base-url>",
        "CANVAS_TOKEN": "<canvas-token>"
      }
    }
  }
}

Requires CANVAS_BASE_URL, CANVAS_TOKEN