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/jonny-1812/corebee-mcp-skillsWrote 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/jonny-1812/corebee-mcp-skills/corebee)<a href="https://agentmods.dev/mcp/jonny-1812/corebee-mcp-skills/corebee"><img src="https://agentmods.dev/badge/mcp/jonny-1812/corebee-mcp-skills/corebee/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/jonny-1812/corebee-mcp-skills/corebee"><img src="https://agentmods.dev/badge/mcp/jonny-1812/corebee-mcp-skills/corebee.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
corebee 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 9d 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
{
"corebee": {
"type": "http",
"url": "https://corebee.ai/api/v1/mcp/stream",
"description": "Corebee AI customer support. Manage conversations, contacts, knowledge base, analytics, and widget settings. OAuth is discovered automatically from the server's WWW-Authenticate and .well-known metadata; no inline auth config required."
}
}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.
- 9d ago First seen · 7 lines scan A 0bd45dec2569
corebee is an MCP server published in the GitHub repository jonny-1812/corebee-mcp-skills (0 stars, last pushed 1mo 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 2026-08-30.
Other mcp servers, from other repositories
deskcrew
MCP server "deskcrew", hosted remotely at deskcrew.io, as configured in webmilmind1/deskcrew-mcp.
support
Agent-native helpdesk where AI agents run support tickets and pay per action in USDC via x402. Remote server at deskcrew.io.
helpscout
MCP server "helpscout" as configured in drewburchfield/help-scout-mcp-server. Runs dist/cli.js with node. Needs 3 environment variables to run.
help-scout-mcp
Search Help Scout conversations, customers, organizations, threads, and inboxes with AI assistants. Runs locally from the help-scout-mcp-server npm package. Needs 3 environment variables to run.
mcp-freescout
FreeScout ticket management with AI-powered analysis, search filters, and structured outputs. Runs locally from the @verygoodplugins/mcp-freescout npm package. Needs 3 environment variables to run.
shopbot-ai
MCP server "shopbot-ai" as configured in hayamot0/shopbot-ai. Runs locally from the shopbot-ai Python package.