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/CanaryUsers-ai/canaryusers-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/canaryusers-ai/canaryusers-mcp/canaryusers)<a href="https://agentmods.dev/mcp/canaryusers-ai/canaryusers-mcp/canaryusers"><img src="https://agentmods.dev/badge/mcp/canaryusers-ai/canaryusers-mcp/canaryusers.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
canaryusers 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 7d 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
{
"canaryusers": {
"url": "https://www.canaryusers.ai/api/mcp",
"type": "streamable-http"
}
}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.
- 7d ago First seen · 6 lines scan A 755deb7a91e3
canaryusers is an MCP server published in the GitHub repository CanaryUsers-ai/canaryusers-mcp (0 stars, last pushed 2mo ago), 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
sauce-api-mcp
MCP servers for Sauce Labs APIs (Core & RDC OpenAPI). Runs locally from the sauce-api-mcp Python package. Needs 2 environment variables to run.
zendesk-local
MCP server "zendesk-local" as configured in fruggr/zendesk-mcp-server. Launched with pnpm exec tsx src/index.ts --mode all --dev. Needs 1 environment variable to run.
kilotest
Ensemble testing of web pages for accessibility, usability, and standards conformity. Remote server at kilotest.com.
argus
Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis). Runs locally from the argusqa-os npm package.
mcp-server
Test management over MCP: author cases, run manual executions, cut releases, read health. Runs locally from the @m00nsolutions/mcp-server npm package. Needs 5 environment variables to run.
screenshots
Capture screenshots, detect visual regressions between page versions, and analyze with AI. Runs locally from the @snapshot-site/mcp npm package. Needs 1 environment variable to run.