Provides tools for interacting with the Canvas LMS API, allowing users to list courses and filter them by enrollment type (teacher, student, or TA).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Canvas MCP Server list my courses where I'm a student"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server implementation for the Canvas LMS API. This server provides functionality to interact with Canvas LMS programmatically.
List courses from Canvas LMS with optional enrollment type filtering
Interactive help prompts for using the tools
Related MCP server: Canvas Assignment Assistant
Node.js 18 or later
A Canvas LMS instance
Canvas API access token
Cursor (for client integration)
Clone this repository
Install dependencies:
npm installSet up environment variables:
export CANVAS_BASE_URL="https://your-canvas-instance.com"
export CANVAS_ACCESS_TOKEN="your-api-token"Build the project:
npm run buildStart the server:
npm startTo use this MCP server with Cursor:
Open Cursor's settings
Navigate to the MCP configuration section
Add a new server configuration:
{
"mcpServers": {
"canvas": {
"command": "npm",
"args": [
"start"
],
"cwd": "/path/to/mcp-server-canvas"
}
}
}Save the configuration and restart Cursor
The Canvas tools will now be available in Cursor's MCP tools panel
Lists all courses from Canvas LMS.
Parameters:
enrollment_type (optional): Filter courses by enrollment type (teacher, student, ta)
Example response:
{
"content": [
{
"type": "text",
"text": [
{
"id": 1234,
"name": "Example Course",
"code": "EX101",
"state": "available",
"startDate": "2024-01-01T00:00:00Z",
"endDate": "2024-12-31T23:59:59Z"
}
]
}
]
}An interactive prompt that provides help with using the list_courses tool.
The server is built using TypeScript and the MCP SDK. To add new features:
Add new API methods to the CanvasAPI class
Register new tools using server.tool()
Register help prompts using server.prompt()
Build and test your changes
If you encounter issues:
Check that environment variables are set correctly
Verify your Canvas API token has the necessary permissions
Check Cursor's MCP server logs for any error messages
Ensure the server path in Cursor's configuration is correct
MIT
Get courses for a specific user with optional grading count
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | Canvas user ID | |
| include_grading_count | No | Include needs grading count | |
| enrollment_state | No | Filter by enrollment state (active, invited, etc) | active |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe behavioral traits like whether it's read-only, requires authentication, has rate limits, returns paginated results, or what happens on errors. For a tool with no annotations, this leaves significant gaps in understanding how it behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every part of the sentence contributes meaning, and there's no redundancy or fluff. It's appropriately sized for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., course list format, error handling) or behavioral aspects like permissions or side effects. For a tool with three parameters and no structured output documentation, the description should provide more context to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by hinting at the optional grading count feature, but it doesn't provide additional semantic context or usage examples. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get courses for a specific user with optional grading count'. It specifies the verb ('Get'), resource ('courses'), and scope ('for a specific user'), though it doesn't differentiate from siblings since none are provided. The description is not tautological and provides meaningful context beyond the tool name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It mentions an optional feature ('with optional grading count') but doesn't explain when this should be enabled. Without sibling tools, this is less critical, but the description lacks any usage instructions beyond the basic purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_user_coursesScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool has a clear, specific purpose focused on retrieving user courses, leaving no ambiguity for an agent to misselect.
The single tool name follows a consistent verb_noun pattern (get_user_courses), making it predictable and readable. There are no other tools to compare against, so no inconsistency can arise.
One tool is too few for a server named 'Canvas MCP Server', which suggests a broader educational platform scope (e.g., courses, assignments, grades). This minimal set severely limits functionality and feels incomplete for the implied domain.
The tool surface is severely incomplete for a Canvas server, covering only user course retrieval. There are obvious gaps: no CRUD operations for courses, assignments, submissions, or grades, and no ability to create, update, or delete resources, which will cause significant agent failures.
Model Context Protocol server for Studex tools, notifications, and profile integrations
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Create, validate, edit, export (markdown/svg/png/mermaid), and search JSON Canvas files.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
