What are the prerequisites for running Claude Canvas MCP?
You need Node.js v16 or higher, a Canvas API token, a Canvas instance URL (defaults to `http://canvas.docker/`), and the Claude Desktop application.
@johnnyrobot
Basic information
A Claude desktop MCP server for controlling the Canvas LMS REST API
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Claude Canvas MCP is a Model Context Protocol server that enables Claude to interact with Canvas LMS through the Canvas API. It provides tools for managing courses, announcements, assignments, students, files, and more. This server is designed for educators and administrators who use Canvas and want to automate workflows via Claude.
Install dependencies with npm install, build the TypeScript project with npm run build, then configure environment variables in a .env file with your Canvas API token and domain. Finally, add the server to Claude Desktop’s configuration file (claude_desktop_config.json) under mcpServers, pointing to the built index.js and setting CANVAS_API_TOKEN and CANVAS_DOMAIN. Restart Claude Desktop to start using the tools.
You need Node.js v16 or higher, a Canvas API token, a Canvas instance URL (defaults to `http://canvas.docker/`), and the Claude Desktop application.
Set the `CANVAS_API_TOKEN` and `CANVAS_DOMAIN` environment variables in your `.env` file or in the `env` section of the Claude Desktop configuration.
Data stays in your Canvas instance; the server acts as a bridge via the Canvas API and does not store any data locally.
The server runs as a subprocess of Claude Desktop via stdio, as defined by the `command` and `args` in the Claude Desktop configuration.
The server uses a Canvas API token provided via the `CANVAS_API_TOKEN` environment variable.

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil
UnificAlly MCP server. One API for 100+ AI video, image, music and speech models. https://mcp.unifically.com/mcp
NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
Comments