1. You ask the AI (e.g., "Create an assignment due next Friday").
2. The AI detects your intent and communicates with the Canvas MCP Server, sending the required parameters.
3. The server makes a secure call to the official Canvas API.
4. Canvas processes the action and returns the response.
5. The AI confirms the success of the action back to you in plain, natural language.

Use Cases & Examples

Here are some realistic, everyday prompts you can use with your AI assistant:

[!TIP] Token Saving & Efficiency: Whenever possible, specify the Canvas ID or the direct Canvas URL (e.g., https://[your_institution].instructure.com/courses/[course_id]/assignments/[assignment_id]) in your prompts. This prevents the AI from scanning all your courses/resources, leading to faster responses and substantial token savings.

📖 Course Auditing & Querying

• 💬 "What active courses do I have this semester? Check if there are multiple active sections/parallels."
• 💬 "Show me all ungraded submissions for 'Essay 1: Introduction to Sociology' in Sociology 101."
• 💬 "Who is in Student Group A for the Chemistry class?"
• 💬 "Does the assignment 'Project Proposal' have an active rubric associated? If so, retrieve its criteria."
• 💬 "Search for everything related to 'photosynthesis' across my Biology course — assignments, pages, and discussions."

✍️ Creating & Organizing Course Content

• 💬 "Create a new module named 'Week 1: Foundations' in my course."
• 💬 "Add a SubHeader 'REQUIRED READINGS' inside the 'Week 1' module, and link the syllabus page to it."
• 💬 "In my Business course, create an assignment called 'Case Study 1: Market Analysis'. Add an instructions table with columns for Criteria, Requirements, and Points."
• 💬 "Create a threaded discussion topic in my course titled 'Weekly Reflection' and pin it to the top."

💯 Grading & Absence Management

• 💬 "For assignment 'Case Study 1', find all students who haven't submitted their work. Assign them a grade of 0 and add the comment: 'Activity not submitted. Please contact the instructor if you have a valid excuse.'"
• 💬 "Grade John's submission for 'Essay 1' with a 90 based on the rubric, and add a comment: 'Great job! The analysis is well-structured, though you could expand more on the conclusion. Keep it up!'"

📊 Student Engagement & Analytics

• 💬 "Show me the activity analytics for my Calculus course — how active have students been this week?"
• 💬 "Which students haven't been active in course 12345 in the last few days? I want to reach out to them."
• 💬 "Get the analytics for student [ID] in my Biology course — how many page views and participations do they have?"

💬 Messaging & Communication

• 💬 "Send a private message to student [ID] reminding them their 'Project Proposal' is due tomorrow."
• 💬 "How many unread messages do I have in my Canvas inbox?"
• 💬 "Show me my last 10 inbox conversations."

👥 Enrollment & Student Management

• 💬 "Who is enrolled in my course? Show me students and TAs separately."
• 💬 "Search for a student named 'Maria Gonzalez' in account 1."
• 💬 "Enroll user [ID] as a TA in my Physics course."

🔄 Peer Reviews

• 💬 "List all peer review assignments for 'Research Paper' in course 12345."
• 💬 "Manually assign student [ID] to review [other student ID]'s submission for 'Essay 2'."

Setup Guide

To connect your AI assistant to Canvas, you need to configure two things: your Canvas credentials and your AI client (like Claude).

Step 1: Obtain Canvas Credentials

To let the server act on your behalf, it needs permission:

1. Log in to your Canvas LMS account.
2. Go to Account ➡️ Settings in the sidebar menu.
3. Scroll down to the Approved Integrations section and click + New Access Token.
4. Enter a purpose (e.g., "Claude Assistant") and click Generate Token.
5. Copy the generated token immediately and store it somewhere safe (you won't be able to see it again after closing the page).

[!IMPORTANT] You will also need your Canvas Domain. This is the web address of your school/university, for example: myschool.instructure.com.

Step 2: Connect to your AI Client

Option A: Claude Desktop (Desktop Application)

1. Open your Claude Desktop configuration file. On Windows, it is located at: %APPDATA%\Claude\claude_desktop_config.json (On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json)
2. Add the Canvas server configuration under mcpServers:

{
  "mcpServers": {
    "canvas": {
      "command": "npx",
      "args": ["-y", "@charlie.act7/canvas-mcp-server"],
      "env": {
        "CANVAS_API_TOKEN": "YOUR_ACCESS_TOKEN_HERE",
        "CANVAS_API_DOMAIN": "myschool.instructure.com"
      }
    }
  }
}

3. Save the file and restart Claude Desktop. You will see a socket/plug icon indicating the server is successfully connected.

Option B: Claude Code (CLI)

Add the Canvas MCP server directly from your terminal:

claude mcp add canvas \
  --env CANVAS_API_TOKEN=YOUR_ACCESS_TOKEN_HERE \
  --env CANVAS_API_DOMAIN=myschool.instructure.com \
  -- npx -y @charlie.act7/canvas-mcp-server

Verify the server is connected:

claude mcp list

CLI Configuration

If you prefer to configure your credentials locally for development, run:

npx @charlie.act7/canvas-mcp-server config

This will guide you step-by-step to input your domain and API token, storing them securely in a local configuration file.

Supported Tools & Resources

Tool Inventory

Supported MCP Resources

For clients supporting direct resources:

• canvas://courses/{id}/readme — Formatted course summary.
• canvas://courses/{id}/pages/{slug} — Direct HTML content of Canvas pages.

LLM / AI Client Integration

For detailed integration instructions covering Cursor, GitHub Copilot, Cline, OpenAI Custom GPTs, and self-hosted setups, see llms-install.md.

Local Development

To clone this repository and modify the code:

1. Install Dependencies:

   npm install
   

2. Build the Project (TypeScript to JavaScript):

   npm run build
   

3. Start Server in Stdio Mode (MCP):

   npm start
   

4. Start HTTP Server with Swagger Documentation: If you want to use this as an OpenAI G