canvas-api-mcp
An MCP server for Canvas LMS that provides 15 curated tools for everyday student work and a gateway to reach every endpoint your Canvas instance exposes.
README
<!-- mcp-name: io.github.JohannsenLum/canvas-api-mcp -->
canvas-api-mcp
<h2 align="center">Never miss an assignment deadline again.</h2>
<p align="center"> Ask your AI what's due and it reads the answer straight from Canvas —<br> real deadlines, real submission status, no copying anything across. </p>
An MCP server for Canvas LMS. 16 curated tools for everyday student work, plus a gateway that reaches every endpoint your Canvas instance exposes.
<p align="center"> <img src="https://raw.githubusercontent.com/JohannsenLum/canvas-api-mcp/main/assets/header.svg" alt="Terminal. Question one: 'what mods am I taking this sem?' — answered instantly by the curated my_courses tool (CS3230, CS2040S, MA2001, GEA1000). Question two: 'what groups am I in?' — no curated tool covers it, so search_canvas_api finds GET /v1/users/self/groups among 1,116 Canvas endpoints and canvas_request executes it. 18 tools · 1,116 endpoints reachable · 149 tests · MIT." width="840"> </p>
📖 Documentation: mcp.johannsenlum.com/canvas-lms — install guide · tool reference · skills · compliance
Personal-use software. Canvas's API Policy requires OAuth for applications used by multiple people, and Canvas OAuth cannot be implemented safely by locally installed software (no PKCE, and
client_secretcannot be shipped in a package). Use this with your own token on your own account. See Compliance.
What you can ask it
Real prompts, and which tool answers them.
You: What's due this week? Claude: (calls
whats_due) — You have 3 things due: Problem Set 4 (Thu, CS3230), a discussion reply (Fri, IS4302), and the Milestone 2 report (Sun, EE2211).
You: How am I doing in my databases course, and what's on the syllabus for week 6? Claude: (calls
my_grades, thenget_pagefor the syllabus, thencourse_contentfor the week 6 module) — You're at 87% overall. Week 6 covers normalization and has a reading plus a lab file due Friday.
You: Summarize the PDF lecture notes for lecture 8 and pull up my submission for the essay so I can see the feedback. Claude: (calls
list_files+read_filefor the PDF, thenmy_submissionfor the essay) — ...
You: Reply to the "Project teams" discussion and say I'm free after 3pm for the group meeting. Claude: (calls
post_discussion_reply✏️) — Posted to the thread.
You: Has Canvas ever given me quiz statistics broken down by question, across the whole semester? Claude: (calls
search_canvas_apito find the right endpoint, thencanvas_requestto call it) — ...
The last example is the point of the gateway tools: if an endpoint exists on your
Canvas instance, search_canvas_api can find it and canvas_request can call it,
even though only 16 tools are hand-curated.
Install
Prerequisites
- Python 3.11+
- A Canvas personal access token. Your institution must allow students to create them: check Canvas → Account → Settings → Approved Integrations for a "+ New access token" button. Full walkthrough with screenshots: mcp.johannsenlum.com/canvas-lms/install.
Running the server
canvas-api-mcp is published on PyPI. Run it with:
uvx canvas-api-mcp
Install from source (contributors / unreleased main). Not part of the
normal install path above — only needed if you want the latest unreleased
code instead of the published PyPI release:
uvx --from git+https://github.com/JohannsenLum/canvas-api-mcp canvas-api-mcp
Or run from a local clone:
git clone https://github.com/JohannsenLum/canvas-api-mcp
cd canvas-api-mcp
uv sync
Quick install (one-click)
One-click deeplinks exist for Cursor, VS Code, and LM Studio only — no other
client has a documented install-link format. These prefill the config below but
still need CANVAS_BASE_URL and CANVAS_TOKEN filled in afterward.
All clients (manual config)
Your token stays on your machine, in your own config file. It is never transmitted anywhere except directly to your Canvas instance.
| Client | Deeplink? |
|---|---|
| Claude Code | no |
| Claude Desktop | no |
| Cursor | yes, above |
| VS Code | yes, above |
| LM Studio | yes, above |
| Zed | no |
| Windsurf | no (Windsurf only resolves servers in its own registry) |
<a id="config-claude-code"></a> <details> <summary><strong>Claude Code</strong> — <code>~/.claude.json</code></summary>
{
"mcpServers": {
"canvas": {
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-claude-desktop"></a> <details> <summary><strong>Claude Desktop</strong> — <code>claude_desktop_config.json</code></summary>
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
No one-click install exists for Claude Desktop (it installs .mcpb bundles, not
deeplinks) — copy this JSON in via Settings → Developer → Edit Config:
{
"mcpServers": {
"canvas": {
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-cursor"></a> <details> <summary><strong>Cursor</strong> — <code>~/.cursor/mcp.json</code></summary>
Fallback for the button above, or if you'd rather paste it directly:
{
"mcpServers": {
"canvas": {
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-vscode"></a> <details> <summary><strong>VS Code</strong> — <code>.vscode/mcp.json</code></summary>
Fallback for the button above, or if you'd rather paste it directly. Note VS
Code uses a servers key, not mcpServers:
{
"servers": {
"canvas": {
"type": "stdio",
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-lmstudio"></a> <details> <summary><strong>LM Studio</strong> — <code>mcp.json</code> (Program → Install → Edit mcp.json)</summary>
Fallback for the button above, or if you'd rather paste it directly:
{
"mcpServers": {
"canvas": {
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-zed"></a> <details> <summary><strong>Zed</strong> — <code>settings.json</code></summary>
No deeplink exists for Zed — add this under context_servers in your Zed
settings:
{
"context_servers": {
"canvas": {
"source": "custom",
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
<a id="config-windsurf"></a> <details> <summary><strong>Windsurf</strong> — <code>~/.codeium/windsurf/mcp_config.json</code></summary>
No deeplink exists for Windsurf — it only resolves servers from its own registry, so this has to be pasted in manually via Windsurf Settings → MCP Servers → Edit raw config:
{
"mcpServers": {
"canvas": {
"command": "uvx",
"args": ["canvas-api-mcp"],
"env": {
"CANVAS_BASE_URL": "https://canvas.yourschool.edu",
"CANVAS_TOKEN": "your-token-here"
}
}
}
}
</details>
Tools
| Tool | What it does |
|---|---|
whoami |
Identity and your role in each course |
get_calendar_feed_url |
Your private calendar .ics link — only when you ask for it |
my_courses |
Active courses with code, term, role |
whats_due |
Everything due, soonest first |
my_grades |
Current score per course |
list_assignments |
A course's assignments and submission state |
get_assignment |
One assignment in full, with rubric |
my_submission |
Your submission, score, and feedback |
submit_assignment ✏️ |
Submit work |
course_announcements |
Recent announcements |
course_content |
Modules and their contents |
list_files |
Files in a course |
read_file |
Extract text from PDF/DOCX/PPTX/text |
get_page |
A Canvas page, e.g. the syllabus |
read_discussion |
Topics, or one topic's replies |
post_discussion_reply ✏️ |
Post to a discussion |
search_canvas_api |
Find any endpoint by keyword (gateway) |
canvas_request ✏️ |
Execute any endpoint (gateway) |
✏️ writes to Canvas. That's 3 write tools total: submit_assignment,
post_discussion_reply, and canvas_request when called with a non-GET method
(GET calls through canvas_request are read-only).
search_canvas_api + canvas_request reach all ~1,116 endpoints your instance
exposes. What they may do is decided by Canvas from your token's permissions — a
teacher token unlocks educator endpoints with no change to this server.
Prompts
week_ahead, study_pack, grade_check.
Resources
canvas://me, canvas://courses, canvas://api/catalog.
Skills
If your client supports the skills convention:
npx skills add JohannsenLum/canvas-api-mcp
Other institutions
Works with any Canvas instance — set CANVAS_BASE_URL. The catalog of ~1,116
endpoints ships inside the package at
canvas_api_mcp/data/catalog.json. To match your deployment's exact feature
set, regenerate it:
python scripts/build_catalog.py https://canvas.yourschool.edu -o data/catalog.json
Compliance
- Academic integrity.
submit_assignmentcan submit anything, including AI-generated work. Submitting work that is not your own breaches the academic integrity rules of essentially every institution, and Canvas's API Policy explicitly prohibits use that violates them. That is on you. - Rate limiting. The client throttles against Canvas's published quota. Do not remove it — overloading the API is prohibited.
- Course material.
read_filefetches materials for your own study. Do not redistribute them. - Your token is password-equivalent. It can read your grades and submit work as you. Set an expiry. Never commit it.
- Personal-use scope. Phase 1 targets a single student using their own token. There are no curated educator tools; Canvas's OAuth flow has no PKCE, so this locally-installed server cannot implement the multi-user OAuth that Canvas's API Policy requires for anything broader. Do not repackage this as a multi-tenant service.
Development
uv sync
uv run pytest -v
# Live tests against your real account (read-only)
CANVAS_LIVE_TESTS=1 uv run pytest tests/test_live.py -v
Environment variables: CANVAS_BASE_URL, CANVAS_TOKEN, optional
CANVAS_MAX_PAGES (default 10). See env.template.
Contributing
Issues and pull requests are welcome — see CONTRIBUTING.md for setup, the architectural rules worth knowing before you change anything, and the bar for adding a new curated tool.
Found a security problem? Do not open a public issue. See SECURITY.md for private reporting — particularly important here, since this project handles password-equivalent Canvas tokens.
Changes are recorded in CHANGELOG.md.
Licence
MIT © 2026 Johannsen Lum.
Use it, change it, redistribute it, build something commercial on it — the only condition is that you keep the copyright notice and licence text. It comes with no warranty of any kind.
Contributions are accepted under the same licence.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。