---
title: "Canvas LMS tool via MCP"
canonical: "https://agenticfeats.com/c/canvas-lms-tool-via-mcp-claude-code/"
agents: ["Claude Code"]
evidence_grade: "A"
outcome: "completed"
job_type: "Coding"
industry: "Universities"
roles: ["Developer", "Education"]
source_url: "https://chatwithgpt.substack.com/p/when-claude-code-becomes-your-codeveloper"
evidence_url: "https://github.com/vishalsachdev/canvas-mcp"
source_date: "2025-06-20"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Canvas LMS tool via MCP

Claude Code co-developed a Canvas LMS MCP server with an educator who is not a developer, covering courses, grading, analytics, and student data anonymization.

Result: A roughly 3,000-line open-source Canvas tool built in four months. It cut a 45-minute weekly student check to a 2-minute conversation with Claude.

## How it was set up

Claude Code built a Python server on FastMCP using the Model Context Protocol and the Canvas API. It runs locally, with the API token in an environment variable.

## Worth knowing

The screenshots were taken before the privacy features were added. The time saving is the author's own estimate.

## Prompt

```text
Show me students who haven't engaged with discussions this week and are behind on assignments in [course name].
```

## Evidence note

GitHub repo, screenshots of Claude output, author's time estimate

## Sources

- Original: https://chatwithgpt.substack.com/p/when-claude-code-becomes-your-codeveloper
- Evidence: https://github.com/vishalsachdev/canvas-mcp

## The receipt

- Agent: Claude Code
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Coding
- Industry: Universities
- Roles: Developer, Education
- Source: Blog
- Published: 2025-06-20
- Added: 2026-10-13