Canvas MCP Server

Instructions

    Args:
        course_identifier: The Canvas course code (e.g., badm_554_120251_246794) or ID
        include_criteria: Whether to include detailed criteria and ratings (default: True)
    

Implementation Reference

• src/canvas_mcp/tools/rubrics.py:790-880 (handler)

  The handler function that implements the list_all_rubrics MCP tool. It fetches all rubrics for a given course using Canvas API, optionally includes detailed criteria and ratings, and formats them into a readable summary.

  async def list_all_rubrics(course_identifier: str | int,
                            include_criteria: bool = True) -> str:
      """List all rubrics in a specific course with optional detailed criteria.
  
      Args:
          course_identifier: The Canvas course code (e.g., badm_554_120251_246794) or ID
          include_criteria: Whether to include detailed criteria and ratings (default: True)
      """
      course_id = await get_course_id(course_identifier)
  
      # Fetch all rubrics for the course
      rubrics = await fetch_all_paginated_results(f"/courses/{course_id}/rubrics")
  
      if isinstance(rubrics, dict) and "error" in rubrics:
          return f"Error fetching rubrics: {rubrics['error']}"
  
      if not rubrics:
          course_display = await get_course_code(course_id) or course_identifier
          return f"No rubrics found for course {course_display}."
  
      # Get course display name
      course_display = await get_course_code(course_id) or course_identifier
  
      result = f"All Rubrics for Course {course_display}:\n\n"
  
      for i, rubric in enumerate(rubrics, 1):
          rubric_id = rubric.get("id", "N/A")
          title = rubric.get("title", "Untitled Rubric")
          points_possible = rubric.get("points_possible", 0)
          reusable = rubric.get("reusable", False)
          read_only = rubric.get("read_only", False)
          data = rubric.get("data", [])
  
          result += "=" * 80 + "\n"
          result += f"Rubric #{i}: {title} (ID: {rubric_id})\n"
          result += f"Total Points: {points_possible} | Criteria: {len(data)} | "
          result += f"Reusable: {'Yes' if reusable else 'No'} | "
          result += f"Read-only: {'Yes' if read_only else 'No'}\n"
  
          if include_criteria and data:
              result += "\nCriteria Details:\n"
              result += "-" * 16 + "\n"
  
              for j, criterion in enumerate(data, 1):
                  criterion_id = criterion.get("id", "N/A")
                  description = criterion.get("description", "No description")
                  long_description = criterion.get("long_description", "")
                  points = criterion.get("points", 0)
                  ratings = criterion.get("ratings", [])
  
                  result += f"\n{j}. {description} (ID: {criterion_id}) - {points} points\n"
  
                  if long_description and long_description != description:
                      # Truncate long descriptions to keep output manageable
                      truncated_desc = truncate_text(long_description, 150)
                      result += f"   Description: {truncated_desc}\n"
  
                  if ratings:
                      # Sort ratings by points (highest to lowest)
                      sorted_ratings = sorted(ratings, key=lambda x: x.get("points", 0), reverse=True)
  
                      for rating in sorted_ratings:
                          rating_description = rating.get("description", "No description")
                          rating_points = rating.get("points", 0)
                          rating_id = rating.get("id", "N/A")
  
                          result += f"   - {rating_description} ({rating_points} pts) [ID: {rating_id}]\n"
  
                          # Include long description if it exists and differs
                          rating_long_desc = rating.get("long_description", "")
                          if rating_long_desc and rating_long_desc != rating_description:
                              truncated_rating_desc = truncate_text(rating_long_desc, 100)
                              result += f"     {truncated_rating_desc}\n"
                  else:
                      result += "   No rating scale defined for this criterion.\n"
          elif include_criteria:
              result += "\nNo criteria defined for this rubric.\n"
  
          result += "\n"
  
      # Add summary
      result += "=" * 80 + "\n"
      result += f"Total Rubrics Found: {len(rubrics)}\n"
  
      if include_criteria:
          result += "\nNote: Use the criterion and rating IDs shown above with the grade_with_rubric tool.\n"
          result += "Example: {\"criterion_id\": {\"points\": X, \"comments\": \"...\", \"rating_id\": \"rating_id\"}}\n"
      else:
          result += "\nTo see detailed criteria and ratings, run this command with include_criteria=True.\n"
  
      return result

• src/canvas_mcp/server.py:51-51 (registration)

  The call to register_rubric_tools(mcp) within register_all_tools, which registers the list_all_rubrics tool among other rubric tools.

  register_rubric_tools(mcp)

• src/canvas_mcp/tools/__init__.py:7-7 (registration)

  Import of register_rubric_tools from rubrics.py, enabling its use in server.py for tool registration.

  from .rubrics import register_rubric_tools