Canvas MCP Server

TypeScript code execution API for Canvas MCP

Remote serverstreamable-httpPython

What is the Canvas MCP MCP server?

If you want an AI assistant working directly with Canvas MCP, the canvas mcp mcp server is the bridge. TypeScript code execution API for Canvas MCP.

What Canvas MCP does

MCP server for Canvas LMS with 99 tools and 8 agent skills. Works with Claude Desktop, Cursor, Codex, Windsurf, and 40+ other agents.

The Canvas MCP Server bridges the gap between AI assistants and Canvas Learning Management System, providing both students and educators with an intelligent interface to their Canvas environment. Built on the Model Context Protocol (MCP), it enables natural language interactions with Canvas data through any MCP-compatible client.

Tools it exposes

Once connected, the assistant can call these 3 tools directly:

  • Approach — Best For
  • bulk_grade_submissions — Batch grading 10-29 items
  • execute_typescript — 30+ items, custom logic

Installing the canvas mcp mcp server

The server is distributed via npm as skills, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 2 environment variables: CANVAS_API_TOKEN, CANVAS_API_URL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  • Python 3.10+ - Required for modern features and type hints - Canvas API Access - API token and institution URL - MCP Client - Any MCP-compatible client (Claude Desktop, Cursor, Zed, Windsurf, Continue, etc.)

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Canvas MCP sits in that group, and the shape of its toolset — Approach, bulk_grade_submissions, execute_typescript — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by vishalsachdev, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the canvas mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
ApproachBest For
bulk_grade_submissionsBatch grading 10-29 items
execute_typescript30+ items, custom logic

How to install the Canvas MCP MCP server

{
  "mcpServers": {
    "canvas-api": {
      "command": "/absolute/path/to/canvas-mcp/.venv/bin/canvas-mcp-server"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.10+ - Required for modern features and type hints - Canvas API Access - API token and institution URL - MCP Client - Any MCP-compatible client (Claude Desktop, Cursor, Zed, Windsurf, Continue, etc.)
VariableDescriptionRequired
CANVAS_API_TOKENCredential the server authenticates with.Yes
CANVAS_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Canvas MCP to Approach.
  • Use Canvas MCP to bulk grade submissions.
  • Use Canvas MCP to execute typescript.

Frequently asked questions

It connects Canvas MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Approach, bulk_grade_submissions, execute_typescript) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Canvas MCP directly.