Summary
If you're a student tired of Canvas's scattered interface and want programmatic access to your courses, assignments, and notifications, this server wraps the Canvas LMS REST API into ten MCP tools: list_courses, list_assignments, list_modules, get_grades, planner_items, and more. It runs locally over stdio with your personal access token stored in a chmod 600 env file, so no credentials leave your machine except in direct HTTPS calls to Canvas. The repo includes a bulk dump script that pulls every file you have access to for offline indexing. Alpha status, single Python file, MIT licensed.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
13 tools
get_coursesRetrieve all available Canvas courses for the current user. Returns a dictionary mapping course names to their corresponding IDs.
Retrieve all available Canvas courses for the current user. Returns a dictionary mapping course names to their corresponding IDs.
No parameter schema in public metadata yet.
get_modulesRetrieve all modules within a specific Canvas course.1 params
Retrieve all modules within a specific Canvas course.
Parameters* required
course_idstringThe unique identifier for the Canvas course. Can be found in the course URL or via get_courses.
get_module_itemsRetrieve all items within a specific module in a Canvas course.2 params
Retrieve all items within a specific module in a Canvas course.
Parameters* required
course_idstringThe unique identifier for the Canvas course. Can be found in the course URL or via get_courses.
module_idstringThe unique identifier for the module within the course. Can be found via get_modules.
get_file_urlGet the direct download URL for a file stored in Canvas.2 params
Get the direct download URL for a file stored in Canvas.
Parameters* required
file_idstringThe unique identifier for the file. Can be found in module items or file listings.
course_idstringThe unique identifier for the Canvas course. Can be found in the course URL or via get_courses.
get_course_assignmentsRetrieve all assignments for a specific Canvas course.2 params
Retrieve all assignments for a specific Canvas course.
Parameters* required
bucketstringOptional filter for assignment status. Valid values: past, overdue, undated, ungraded, unsubmitted, upcoming, future.
course_idstringThe unique identifier for the Canvas course. Can be found in the course URL or via get_courses.
get_assignments_by_course_nameRetrieve all assignments for a Canvas course using its name.2 params
Retrieve all assignments for a Canvas course using its name.
Parameters* required
bucketstringOptional filter for assignment status. Valid values: past, overdue, undated, ungraded, unsubmitted, upcoming, future.
course_namestringThe name of the course to search for. Partial matches are supported (e.g., 'Biology' will match 'Introduction to Biology').
get_canvas_coursesAlias for get_courses - retrieve all Canvas courses.
Alias for get_courses - retrieve all Canvas courses.
No parameter schema in public metadata yet.
get_gradescope_coursesRetrieve all Gradescope courses for the current user.
Retrieve all Gradescope courses for the current user.
No parameter schema in public metadata yet.
get_gradescope_course_by_nameFind a Gradescope course by name.1 params
Find a Gradescope course by name.
Parameters* required
course_namestringThe name of the Gradescope course to search for. Partial matches are supported.
get_gradescope_assignmentsRetrieve all assignments for a Gradescope course.1 params
Retrieve all assignments for a Gradescope course.
Parameters* required
course_idstringThe unique identifier for the Gradescope course. Can be found via get_gradescope_courses or get_gradescope_course_by_name.
get_gradescope_assignment_by_nameFind a Gradescope assignment by name.2 params
Find a Gradescope assignment by name.
Parameters* required
course_idstringThe unique identifier for the Gradescope course. Can be found via get_gradescope_courses or get_gradescope_course_by_name.
assignment_namestringThe name of the assignment to search for. Partial matches are supported.
get_cache_statsGet cache statistics for debugging purposes. Returns hit/miss counts and cache size.
Get cache statistics for debugging purposes. Returns hit/miss counts and cache size.
No parameter schema in public metadata yet.
clear_cacheClear all cached data. Use this if you need fresh data from Canvas or Gradescope.
Clear all cached data. Use this if you need fresh data from Canvas or Gradescope.
No parameter schema in public metadata yet.
canvas-mcp
Local-first MCP server for Canvas LMS. Stdio transport, no network round-trips beyond the official Canvas API.
Status: alpha. Single-user, no warranty, API surface may still shift. File issues if it breaks.
Why
Canvas is built for instructors. As a student you get a fragmented UI, no cross-course search, and notifications that arrive late or never. This server exposes the Canvas REST API as MCP tools so you can drive the LMS from any MCP-compatible client (Claude Code, Claude Desktop, etc.).
Architecture
[client] ──stdio──> [server.py] ──https──> [Canvas API]
- Token lives in
~/.canvas.env(chmod 600) - Server runs locally, no third party in the path
- Single file, fully auditable
Tools exposed
list_courses, list_assignments, list_modules, list_announcements, get_page, get_file_info, get_grades, planner_items, upcoming_events, todo.
Setup
1. Mint a Canvas personal access token
In Canvas: Account → Settings → Approved Integrations → + New Access Token. Copy the token shown — it is not retrievable afterwards.
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 .
Then create the env file:
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
3. Register with your MCP client
Claude Code:
claude mcp add canvas-local -- canvas-local-mcp
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"canvas-local": {
"command": "canvas-local-mcp"
}
}
}
Bulk dump
canvas-local-mcp-dump downloads every file the user has access to (course materials, syllabi). Useful 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.
License
MIT — see LICENSE.
Built by AGENTE 404 S.L. · admin@agente404.com
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Configuration
CANVAS_BASE_URL*Canvas institution root URL (no /api/v1 suffix), e.g. https://your-institution.instructure.com
CANVAS_TOKEN*secretCanvas personal access token (Account -> Settings -> Approved Integrations -> New Access Token)
Categories
Registryactive
Packagecanvas-local-mcp
TransportSTDIO
AuthRequired
UpdatedMay 12, 2026
