Canvas LMS MCP server
✓ VerifiedLets an AI client access Canvas courses, assignments, deadlines, modules, and grades via the Canvas REST API.
Also known as admin978/canvas-mcp, canvas-local-mcp
- Stars
- 4
- Tools
- 10
- Downloads, 30 days
- 112
- Latest version
- 0.1.3
- Last commit
- Jul 23, 2026
- License
- MIT
What is Canvas LMS MCP?
Canvas LMS lets an AI client access Canvas courses, assignments, deadlines, modules, and grades via the Canvas REST API. It exposes 10 tools, such as list_courses, list_assignments, list_modules.
Summary generated from the project's README
About Canvas LMS MCP server
Managing educational workflows by querying Canvas LMS data directly from an AI client is what this local-first MCP server enables. Students and educators can use it to interact with their courses, assignments, and grades through Claude Desktop, Claude Code, or other compatible clients. By converting Canvas REST API actions into accessible tools, it allows for natural language queries regarding academic schedules and course content.
Setup requires Python 3.10 or higher and a personal access token generated from your Canvas account settings. Users must configure a local environment file containing their institution's base URL and their private token. The server operates via stdio transport, ensuring that requests move from your local machine to official Canvas API endpoints without an external token broker.
Beyond real-time queries, the package includes a utility to download course files and content for offline indexing. This provides a way to create a local repository of academic materials for more intensive AI workflows. The available toolset includes functions for listing modules, fetching announcements, checking grades, and viewing upcoming planner items.
What you can do with it
- 1Track academic deadlinesAsk your AI client to identify all assignments that are due within the current week across every active course.
- 2Monitor academic performanceRequest a summary of your current grades organized by their respective courses.
- 3Review course materialsRetrieve specific course modules or syllabus pages to understand lesson structures.
- 4Prepare for upcoming tasksCheck your upcoming events and planner items to organize your schedule for the following week.
Written from the project's README. Every use case is checked against a quote from it.
How to install Canvas LMS MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Canvas LMS MCP in Claude Code
$ claude mcp add --env 'CANVAS_TOKEN=<YOUR_CANVAS_TOKEN>' --env 'CANVAS_BASE_URL=<CANVAS_BASE_URL>' canvas-mcp -- uvx canvas-local-mcpInstall Canvas LMS MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"canvas-mcp": {
"command": "uvx",
"args": [
"canvas-local-mcp"
],
"env": {
"CANVAS_TOKEN": "<YOUR_CANVAS_TOKEN>",
"CANVAS_BASE_URL": "<CANVAS_BASE_URL>"
}
}
}
}Install Canvas LMS MCP in VS Code
.vscode/mcp.json
{
"servers": {
"canvas-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"canvas-local-mcp"
],
"env": {
"CANVAS_TOKEN": "<YOUR_CANVAS_TOKEN>",
"CANVAS_BASE_URL": "<CANVAS_BASE_URL>"
}
}
}
}Install Canvas LMS MCP in VS Code CLI
$ code --add-mcp '{"name":"canvas-mcp","type":"stdio","command":"uvx","args":["canvas-local-mcp"],"env":{"CANVAS_TOKEN":"<YOUR_CANVAS_TOKEN>","CANVAS_BASE_URL":"<CANVAS_BASE_URL>"}}'Install Canvas LMS MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"canvas-mcp": {
"command": "uvx",
"args": [
"canvas-local-mcp"
],
"env": {
"CANVAS_TOKEN": "<YOUR_CANVAS_TOKEN>",
"CANVAS_BASE_URL": "<CANVAS_BASE_URL>"
}
}
}
}Install Canvas LMS MCP in Codex
$ codex mcp add canvas-mcp --env 'CANVAS_TOKEN=<YOUR_CANVAS_TOKEN>' --env 'CANVAS_BASE_URL=<CANVAS_BASE_URL>' -- uvx canvas-local-mcpInstall Canvas LMS MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.canvas-mcp] command = "uvx" args = ["canvas-local-mcp"] [mcp_servers.canvas-mcp.env] CANVAS_TOKEN = "<YOUR_CANVAS_TOKEN>" CANVAS_BASE_URL = "<CANVAS_BASE_URL>"
Install Canvas LMS MCP in Gemini CLI
$ gemini mcp add -s user -e 'CANVAS_TOKEN=<YOUR_CANVAS_TOKEN>' -e 'CANVAS_BASE_URL=<CANVAS_BASE_URL>' canvas-mcp uvx -- canvas-local-mcpInstall Canvas LMS MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"canvas-mcp": {
"command": "uvx",
"args": [
"canvas-local-mcp"
],
"env": {
"CANVAS_TOKEN": "<YOUR_CANVAS_TOKEN>",
"CANVAS_BASE_URL": "<CANVAS_BASE_URL>"
}
}
}
}Canvas LMS MCP tools 10
Detected from the READMElist_courseslist_assignmentslist_moduleslist_announcementsget_pageget_file_infoget_gradesplanner_itemsupcoming_eventstodo
| list_courses | — | |
| list_assignments | — | |
| list_modules | — | |
| list_announcements | — | |
| get_page | — | |
| get_file_info | — | |
| get_grades | — | |
| planner_items | — | |
| upcoming_events | — | |
| todo | — |
Configuration
CANVAS_TOKENRequiredSecretCanvas personal access token (Account -> Settings -> Approved Integrations -> New Access Token)
CANVAS_BASE_URLRequiredCanvas institution root URL (no /api/v1 suffix), e.g. https://your-institution.instructure.com
| Name | Description | |
|---|---|---|
| CANVAS_TOKEN | Canvas personal access token (Account -> Settings -> Approved Integrations -> New Access Token) | RequiredSecret |
| CANVAS_BASE_URL | Canvas institution root URL (no /api/v1 suffix), e.g. https://your-institution.instructure.com | Required |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableadmin978/canvas-mcp is public and reachablegithub.com/admin978/canvas-mcp ↗Pass
- Package names this repository as its sourcecanvas-local-mcp names admin978/canvas-mcp as sourcepypi.org/project/canvas-local-mcp/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-07-24github.com/admin978/canvas-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from canvas-local-mcpPass
- No critical advisory in the package or its dependencies30 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model10 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCanvas LMS MCP Server (canvas-mcp)
Ask Claude about your Canvas courses, assignments, deadlines, modules, and grades from one place.
canvas-mcp is a local-first MCP server for Canvas LMS users (students, instructors, and MCP builders). It turns Canvas REST API actions into MCP tools that work from Claude Code, Claude Desktop, and other MCP-compatible clients.
Status: alpha. Single-user, no warranty, API surface may still shift. File issues if it breaks.
Who this is for
- Students who want one view across multiple courses
- Educators who want faster access to assignments, modules, and announcements
- MCP users who want Canvas data in local Claude workflows
What you can ask Claude
- “What assignments are due this week across all my active courses?”
- “Show upcoming events and planner items for next week.”
- “List my current grades by course.”
- “Get the modules (with items) for course
12345.” - “Show announcements for course
12345.” - “Fetch the page
syllabusfrom course12345.”
Quick start
Prerequisite: Python 3.10+.
1) Create a Canvas personal access token
In Canvas: Account → Settings → Approved Integrations → + New Access Token. Copy the token shown (Canvas does not show it again later).
2) Install
From PyPI (recommended):
pip install canvas-local-mcp
Or from source:
git clone https://github.com/admin978/canvas-mcp.git && cd canvas-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
3) Configure ~/.canvas.env
curl -fsSL https://raw.githubusercontent.com/admin978/canvas-mcp/main/.canvas.env.example -o ~/.canvas.env
chmod 600 ~/.canvas.env
# edit ~/.canvas.env: set CANVAS_BASE_URL (institution root, no /api/v1)
# and paste the token into CANVAS_TOKEN
For token safety guidance (least privilege, file permissions, rotation/revocation, and vulnerability reporting), see SECURITY.md.
4) Register in your MCP client
Claude Code:
claude mcp add canvas-local -- canvas-local-mcp
Claude Desktop:
- macOS example path:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows example path:
%APPDATA%\Claude\claude_desktop_config.json - Linux example path:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"canvas-local": {
"command": "canvas-local-mcp"
}
}
}
Tools exposed
list_courseslist_assignmentslist_moduleslist_announcementsget_pageget_file_infoget_gradesplanner_itemsupcoming_eventstodo
Bulk dump
canvas-local-mcp-dump downloads course files and related content for offline indexing.
canvas-local-mcp-dump # all active courses
canvas-local-mcp-dump 12345 67890 # specific course IDs
Output goes to ./canvas-dump/ by default. Override with CANVAS_DUMP_DIR=/path/to/dir.
Local-first, privacy and token flow
- The server runs locally and uses stdio transport with your MCP client.
- Configuration is read from
~/.canvas.env(CANVAS_BASE_URL,CANVAS_TOKEN). - Requests go from your local server to the official Canvas API endpoints.
- No external token broker is used in the request path.
- Security guidance and disclosure policy: SECURITY.md.
Demo
No demo GIF is currently committed yet. You can still verify the workflow quickly:
Try these prompts
After registering the MCP server, ask Claude:
- “List my active Canvas courses.”
- “What assignments are due this week across all my active courses?”
- “Show upcoming events and planner items for next week.”
- “List my current grades by course.”
Placeholder: add a short terminal/GIF walkthrough here in a future PR.
Development
Requires Python 3.10+.
pip install -e ".[dev]"
ruff check canvas_local_mcp tests # lint
pytest # tests run against a mocked Canvas API — no token needed
CI runs lint + tests on Python 3.10–3.13 for every push and pull request.
Publishing a new release
Follow this order to publish a new version (e.g. 0.1.4) consistently across PyPI and the MCP Registry.
1. Bump the version everywhere
Update all three files to the new version string in a single PR:
| File | Field |
|---|---|
pyproject.toml |
[project].version |
canvas_local_mcp/__init__.py |
__version__ |
server.json |
root version and packages[0].version |
The CI test test_server_json_version_matches_package and the workflow validation step will fail if any of these three disagree.
2. Merge the PR into main
Wait for all CI checks to pass before merging.
3. Publish canvas-local-mcp to PyPI
The project uses Trusted Publisher (OIDC) for PyPI uploads.
Trigger the PyPI publish workflow (or run python -m build && twine upload dist/* if you have credentials configured) before creating the tag, so the package is available when the MCP Registry fetches it.
4. Create and push the tag vX.Y.Z
git tag v0.1.4
git push origin v0.1.4
This triggers the Publish to MCP Registry workflow, which:
- Validates that
server.json,pyproject.toml, and the tag all declare the same version. - Publishes
server.jsonto the MCP Registry via GitHub OIDC (no secrets needed).
5. Verify
- PyPI:
https://pypi.org/project/canvas-local-mcp/ - MCP Registry:
https://registry.modelcontextprotocol.io/?q=canvas-mcp - GitHub Actions:
https://github.com/admin978/canvas-mcp/actions
Important: never reuse or move an existing tag. If you need to re-publish after a mistake, bump to the next patch version (e.g.
0.1.4) and start from step 1.
Contributing, roadmap and support
- Issues / feature requests
- Pull requests are welcome for bug fixes and Canvas workflow improvements
- Roadmap direction currently lives in open issues and upcoming PRs
If this project helps you manage Canvas with Claude, please try the flow above and consider giving it a ⭐ so other students and educators can find it.
License
MIT — see LICENSE.
Built by AGENTE 404 S.L. · admin@agente404.com
Canvas LMS MCP questions
How do I add Canvas LMS MCP to Claude Code?
Run claude mcp add --env 'CANVAS_TOKEN=<YOUR_CANVAS_TOKEN>' --env 'CANVAS_BASE_URL=<CANVAS_BASE_URL>' canvas-mcp -- uvx canvas-local-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Canvas LMS MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Canvas LMS MCP provide?
It exposes 10 tools, including list_courses, list_assignments, list_modules, list_announcements, get_page.
What can I ask Claude about my Canvas account?
You can ask about assignments due this week, upcoming events, planner items, current grades by course, course modules, announcements, and syllabus pages.
Can I download course content for offline use?
Yes, the canvas-local-mcp-dump tool allows you to download course files and related content for offline indexing.