canvas-pilot — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by X-isdoingreat · MCP Server · ★ 121

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is canvas-pilot safe to install? View the security audit →

About canvas-pilot

Canvas Pilot Website: https://canvas-pilot.likelyou.com Canvas Pilot is a local-first AI agent that learns each Canvas course's recurring assignment pattern, then reuses that pattern through scan - approval - execute. It scans upcoming Canvas LMS assignments, proposes a student-review approval plan, and dispatches approved work into course-specific workflows that produce review-ready drafts and run reports. It is not another Canvas API wrapper. Canvas MCP servers let an agent access Canvas; Canvas Pilot turns repeated course patterns into reusable workflows. Codex is the primary driver. The legacy Claude Code path is preserved while the project completes the migration. Why it is different See Canvas Pilot vs Canvas MCP for the lo

ai-agentai-agentsassignment-plannerassignment-workflowscanvas-agentcanvas-apicanvas-lmsclaude-codecodexcourse-workflows

Quick Facts

Stars121
Forks13
LanguagePython
CategoryMCP Server
LicenseAGPL-3.0
Quality Score69.1542746993931/100
Last Updated2026-07-31
Created2026-05-23
Platformsclaude-code, codex, mcp, python
Est. Tokens~20k

Compatible Skills

These tools work well together with canvas-pilot for enhanced workflows:

  • OpenVoiceUI — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

canvas-pilot alternative? Top 6 similar tools

Looking for a canvas-pilot alternative? If you're comparing canvas-pilot with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • ZeusHammer by pengrambo3-tech · ⭐ 70

    ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

  • Agent_View_Controller-AVC by study8677 · ⭐ 67

    👁️ The visual layer for CLI coding agents. Pipe JSON → interactive native UI → modified JSON back. Like fzf,

  • vnx-orchestration by Vinix24 · ⭐ 61

    Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality ga

  • threadlens by hanityx · ⭐ 57

    Search, review, back up, and safely clean up local sessions from Codex, Claude, Gemini, and Copilot.

  • roam-code by Cranot · ⭐ 518

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is canvas-pilot?

canvas-pilot is Local-first Canvas LMS AI agent that learns each course's recurring assignment workflow and reuses it through scan -> approval -> execute with student review.. It is categorized as a MCP Server with 121 GitHub stars.

What programming language is canvas-pilot written in?

canvas-pilot is primarily written in Python. It covers topics such as ai-agent, ai-agents, assignment-planner.

How do I install or use canvas-pilot?

You can find installation instructions and usage details in the canvas-pilot GitHub repository at github.com/X-isdoingreat/canvas-pilot. The project has 121 stars and 13 forks, indicating an active community.

What license does canvas-pilot use?

canvas-pilot is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to canvas-pilot?

The top alternatives to canvas-pilot on Agent Skills Hub include maestro, ZeusHammer, Agent_View_Controller-AVC. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools