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/antonioac1/courierWrote 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/antonioac1/courier/getcourier)<a href="https://agentmods.dev/mcp/antonioac1/courier/getcourier"><img src="https://agentmods.dev/badge/mcp/antonioac1/courier/getcourier/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/antonioac1/courier/getcourier"><img src="https://agentmods.dev/badge/mcp/antonioac1/courier/getcourier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
getcourier 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 yesterday.
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
{
"getcourier": {
"type": "http",
"url": "https://getcourier.dev/mcp"
}
}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.
- yesterday First seen · 6 lines scan A 1ed8399ad9b8
getcourier is an MCP server published in the GitHub repository antonioac1/courier (0 stars, last pushed 2d 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 2026-11-03.
Other mcp servers, from other repositories
mailflat-mcp
MCP server that gives an AI agent real email inboxes: create, waitforotp, send and more, for Claude Desktop, Cursor and any MCP client. Runs locally from the mailflat-mcp Python package. Needs 2 environment variables to run.
omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform. Remote server at app.omnara.com.
agent-swarm
Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration. Runs locally from the @desplega.ai/agent-swarm npm package. Needs 1 environment variable to run.
mcp-server
Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified. Remote server at api.e2a.dev.
technocore-chat
MCP server for technocore-chat: shared rooms, durable notes and rendezvous for agents, over plain HTTP. Runs locally from the technocore-mcp Python package. Needs 2 environment variables to run.
raxol
MCP server "raxol" as configured in DROOdotFOO/raxol. Launched with mix mcp.server. Needs 1 environment variable to run.