Canvas Mcp
Let your coding agent read and update Canvas LMS courses, assignments, and enrollment data without building custom API glue.
Overview
io.github.admin978/canvas-mcp is a MCP server for the Build phase that connects AI agents to Canvas LMS locally over stdio using your institution URL and access token.
What is this MCP server?
- Local-first stdio MCP—no third-party MCP broker between your machine and Canvas
- PyPI package canvas-local-mcp v0.1.1 with stdio transport
- Requires institution CANVAS_BASE_URL (root URL, no /api/v1) and personal CANVAS_TOKEN
- Suited to edu SaaS, tutoring bots, and course-ops automation from Claude Code or Cursor
- Server version 0.1.1 on PyPI identifier canvas-local-mcp
- Stdio transport only; no remote broker in server schema
Community signal: 1 GitHub stars.
What problem does it solve?
Agents cannot safely or repeatably call Canvas unless you hand-roll API clients and token handling every time.
Who is it for?
Indie builders shipping edu agents, course ops scripts, or LMS-backed SaaS who already have Canvas API tokens.
Skip if: Teams without Canvas, or anyone who needs a hosted multi-tenant LMS product without self-managed tokens.
What do I get? / Deliverables
After install, your agent can query and act on Canvas data through MCP tools while credentials stay on your local runtime.
- Registered local Canvas MCP server in your agent
- Agent-callable Canvas LMS operations via MCP tools
Recommended MCP Servers
Journey fit
Canvas wiring is product integration work—connecting your agent or internal tools to an external LMS API during build. Fits the integrations shelf because the server wraps Instructure Canvas REST access for agent-driven workflows.
How it compares
MCP integration for Canvas LMS, not a standalone learning platform or browser automation skill.
Common Questions / FAQ
Who is io.github.admin978/canvas-mcp for?
Developers and solo builders who use Claude Code, Cursor, or similar agents and need programmatic Canvas LMS access on their own machine.
When should I use io.github.admin978/canvas-mcp?
Use it during build when you are wiring course data, assignments, or instructor workflows into an agent or internal tool against a real Canvas tenant.
How do I add io.github.admin978/canvas-mcp to my agent?
Install the PyPI package canvas-local-mcp, set CANVAS_BASE_URL and CANVAS_TOKEN, register the stdio MCP server in Claude Code or Cursor, then invoke Canvas tools from the agent.