Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git 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/mcp/bruchris/canvas-lms-mcp/canvas-lms)<a href="https://agentmods.dev/mcp/bruchris/canvas-lms-mcp/canvas-lms"><img src="https://agentmods.dev/badge/mcp/bruchris/canvas-lms-mcp/canvas-lms/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/bruchris/canvas-lms-mcp/canvas-lms"><img src="https://agentmods.dev/badge/mcp/bruchris/canvas-lms-mcp/canvas-lms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
canvas-lms 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 12d 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.
What it actually says
{
"canvas-lms": {
"command": "npx",
"args": [
"-y",
"canvas-lms-mcp"
],
"env": {
"CANVAS_API_TOKEN": "${user_config.canvas_api_token}",
"CANVAS_BASE_URL": "${user_config.canvas_base_url}",
"CANVAS_PSEUDONYMIZE_STUDENTS": "${user_config.pseudonymize_students}",
"CANVAS_PSEUDONYMIZE_REVERSE_LOOKUP": "${user_config.pseudonymize_reverse_lookup}"
}
}
}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.
- 12d ago First seen · 15 lines scan A bb7dc3ded50b
canvas-lms is an MCP server published in the GitHub repository bruchris/canvas-lms-mcp (5 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
scorm-mcp-server
Turn HTML or mobile-learning exports into SCORM 2004/1.2 packages, and validate any SCORM zip. Runs locally from the scorm-mcp-server npm package. Needs 1 environment variable to run.
canvas
MCP server "canvas" as configured in 98ping/chip. Runs vendor/canvas-mcp/server/index.js with node. Needs 2 environment variables to run.
canvas-api-mcp
MCP server for Canvas LMS: student tools plus full API gateway. Runs locally from the canvas-api-mcp Python package. Needs 3 environment variables to run.
canvas-student-mcp
MCP server for Canvas LMS that works even when your school disables API tokens — session-cookie auth, read-only by design. 30 tools for Claude and any MCP client. Runs locally from the canvas-student-mcp npm package.
canvas-mcp
Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker. Runs locally from the canvas-local-mcp Python package. Needs 2 environment variables to run.
getcourse-mcp
MCP server that automates a GetCourse account (grant lesson/training access, manage users & groups) through a logged-in browser over CDP. Runs locally from the getcourse-mcp npm package.