Skip to main content
Glama

Canvas MCP Server

weekly-maintenance.yml2.78 kB
name: Weekly Maintenance on: schedule: - cron: '0 0 * * 0' # Every Sunday at midnight UTC workflow_dispatch: # Allow manual trigger jobs: maintenance: runs-on: ubuntu-latest permissions: contents: write issues: write pull-requests: write id-token: write steps: - name: Checkout repository uses: actions/checkout@v4 with: fetch-depth: 0 - name: Set up Python uses: actions/setup-python@v4 with: python-version: '3.11' - name: Install dependencies run: | python -m pip install --upgrade pip pip install -e . - name: Run Claude Maintenance Tasks id: claude-maintenance uses: anthropics/claude-code-action@v1 with: claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }} prompt: | REPO: ${{ github.repository }} Please perform weekly maintenance tasks for this Canvas MCP server project: 1. **Dependency Analysis** - Check pyproject.toml for outdated dependencies - Verify canvasapi library compatibility with latest Canvas API - Check if mcp library has updates - Review Python version requirements 2. **Canvas API Compatibility** - Review recent Canvas API changelog (if accessible via web search) - Identify any deprecated endpoints we're using - Check if new Canvas API features should be added 3. **Code Quality** - Scan for TODO comments older than 30 days - Check for unused imports or dead code - Review error handling patterns 4. **Documentation Health** - Verify README examples are still accurate - Check if new tools need documentation - Ensure CLAUDE.md instructions are current 5. **Issue Management** - Review open issues older than 60 days - Suggest closing stale issues or adding updates - Identify issues that could be "good-first-issue" 6. **Security** - Check for any hardcoded secrets or credentials - Review environment variable usage - Scan for common security anti-patterns Create a detailed maintenance report as a GitHub issue with: - Summary of findings - Actionable recommendations - Priority levels for each item - Links to relevant files/lines Use gh CLI to create the issue with label "maintenance". claude_args: '--allowed-tools "Bash(gh:*),Read,Glob,Grep,WebSearch"'

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vishalsachdev/canvas-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server