Borrowing it
Nothing to install: this file belongs to bruchris/canvas-lms-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bruchris/canvas-lms-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/bruchris/canvas-lms-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/bruchris/canvas-lms-mcp/agents-md)<a href="https://agentmods.dev/instructions/bruchris/canvas-lms-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bruchris/canvas-lms-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01800 | $0.01800 |
| Opus 5 | $0.00900 | $0.00900 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
canvas-lms-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Canvas LMS MCP Server
Guide for AI agents consuming or contributing to canvas-lms-mcp.
Quick Start
# Run with npx (no install needed)
npx canvas-lms-mcp --token $CANVAS_API_TOKEN --base-url https://school.instructure.com
# Or install globally
npm install -g canvas-lms-mcp
canvas-lms-mcp --token $CANVAS_API_TOKEN --base-url $CANVAS_BASE_URL
Environment variables are also supported:
export CANVAS_API_TOKEN=your_token_here
export CANVAS_BASE_URL=https://school.instructure.com
npx canvas-lms-mcp
Architecture
Three-layer design with strict separation of concerns:
Layer 1: src/canvas/ Standalone Canvas REST API client
Pure fetch, no MCP dependency, independently importable
Modular classes composed into CanvasClient facade
Layer 2: src/tools/ MCP tool definitions
Each domain exports (canvas: CanvasClient) => ToolDefinition[]
Zod input schemas, annotations, error formatting
Layer 3: src/server.ts MCP server factory
src/stdio.ts stdio transport (Claude Desktop, Cursor, VS Code)
src/http.ts HTTP transport (ChatGPT, hosted service)
Data Flow
AI Agent --> MCP Transport (stdio/HTTP)
|
McpServer (tool dispatch)
|
ToolDefinition.handler (Zod validation + error catch)
|
CanvasClient.module.method (typed API call)
|
CanvasHttpClient (fetch + auth + pagination)
|
Canvas LMS REST API
Tool Inventory
104 tools total: 76 read-only, 28 write operations.
| Domain | Tools |
|---|---|
| Health | health_check |
| Courses | list_courses, get_course, get_syllabus, create_course, update_course |
| Assignments | list_assignments, get_assignment, list_assignment_groups, create_assignment, update_assignment, delete_assignment |
| Submissions | list_submissions, get_submission, grade_submission, comment_on_submission |
| Rubrics | list_rubrics, get_rubric, get_rubric_assessment, submit_rubric_assessment |
| Quizzes | list_quizzes, get_quiz, list_quiz_submissions, list_quiz_questions, get_quiz_submission_answers, score_quiz_question |
| Files | list_files, list_folders, get_file, upload_file, delete_file |
| Gradebook History | list_gradebook_history_days, get_gradebook_history_day, list_gradebook_history_submissions, get_gradebook_history_feed |
| Users | list_students, get_user, get_profile, search_users, list_course_users |
| Groups | list_groups, list_group_members |
| Enrollments | list_enrollments, enroll_user, remove_enrollment |
| Discussions | list_discussions, get_discussion, list_announcements, post_discussion_entry, create_discussion, update_discussion, delete_discussion |
| Modules | list_modules, get_module, list_module_items, create_module, update_module, create_module_item |
| Pages | list_pages, get_page, create_page, update_page, delete_page |
| Calendar | list_calendar_events, create_calendar_event, update_calendar_event |
| Conversations | list_conversations, get_conversation, get_conversation_unread_count, send_conversation |
| Peer Reviews | list_peer_reviews, get_submission_peer_reviews, create_peer_review, delete_peer_review |
| Accounts | get_account, list_accounts, list_sub_accounts, list_account_courses, list_account_users, get_account_reports |
| Analytics | search_course_content, get_course_analytics, get_student_analytics, get_course_activity_stream |
| Outcomes | get_root_outcome_group, list_outcome_groups, list_outcome_group_links, get_outcome_group, list_outcome_group_outcomes, list_outcome_group_subgroups, get_outcome, get_outcome_alignments, get_outcome_results, get_outcome_rollups, get_outcome_contributing_scores, get_outcome_mastery_distribution |
| Student | get_my_courses, get_my_grades, get_my_submissions, get_my_upcoming_assignments |
| Dashboard | get_dashboard_cards, get_todo_items, get_upcoming_events, get_missing_submissions |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 172 lines · 1,800 tokens per session scan A aed982df7931
canvas-lms-mcp AGENTS.md is an instructions file published in the GitHub repository bruchris/canvas-lms-mcp (4 stars, last pushed today), licensed MIT. It adds 1,800 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.