canvas-mcp-server
Enables AI assistants to automatically pull Canvas LMS course materials into Obsidian, syncing files, assignments, grades, and announcements organized by course and module.
README
Canvas MCP Server
Automatically pull Canvas LMS course materials into Obsidian instead of manually downloading and organizing them.
Why This Exists
Canvas LMS is great for courses, but managing materials requires constant downloads and folder organization. Canvas MCP Server bridges the gap: use an AI assistant to sync course files, assignments, grades, and announcements directly into your Obsidian vault, organized by course and module.
Quick Example
# Your AI assistant runs these MCP tools:
list_courses() # → Find course ID
discover_course_files("123") # → Preview all files/structure
download_course("123", "My Course") # → Sync everything to Obsidian
# Result: Obsidian vault/Canvas/My Course/Modules/Week 1/lecture.pdf (downloaded)
Status
Dormant — Not actively maintained. Provided as-is for reference.
Available Tools
Discovery: list_courses, discover_course_files, get_course_modules
Download: download_file, download_module, download_course, sync_course_files
Info: get_course_assignments, get_course_announcements, get_course_grades, get_upcoming_events
Jobs: get_job_status, list_jobs (for background operations)
Gotchas
Auth Token Setup
- Get from Canvas: Account Settings → Approved Integrations → New Access Token
- Token is required; server won't run without it
Rate Limits
- Canvas API allows ~3000 requests/hour
- Use
background=Trueon large downloads to avoid timeout
File Access Issues
- Server uses 4-strategy fallback (global scope → public URL → course scope → user scope) to work around permission restrictions
- Students with limited Canvas API access still work in most cases
- Rare: if all 4 fail, manually download from Canvas web UI
Setup
Configuration
Environment variables or .env file:
CANVAS_BASE_URL=https://your-canvas-instance.edu
CANVAS_API_TOKEN=<your-token>
OBSIDIAN_VAULT_PATH=C:\path\to\your\vault
CANVAS_FOLDER=Canvas # subfolder in vault (default: Canvas)
PORT=8080
Quick Start
pip install -r requirements.txt
python canvas_server.py
Docker
docker build -t canvas-mcp-server .
docker run -e CANVAS_BASE_URL=... -e CANVAS_API_TOKEN=... \
-v /path/to/obsidian:/obsidian canvas-mcp-server
Tech Stack
- Python 3.11, FastMCP, httpx, python-dotenv, Docker
License
See CLAUDE.md for notes.
Screenshots
TODO (Patrik): add screenshots here.
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。