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/ftaricano/mcp-outlookWrote 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/ftaricano/mcp-outlook/outlook_multi_mailbox)<a href="https://agentmods.dev/mcp/ftaricano/mcp-outlook/outlook_multi_mailbox"><img src="https://agentmods.dev/badge/mcp/ftaricano/mcp-outlook/outlook_multi_mailbox/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/ftaricano/mcp-outlook/outlook_multi_mailbox"><img src="https://agentmods.dev/badge/mcp/ftaricano/mcp-outlook/outlook_multi_mailbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
outlook_multi_mailbox 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 10d 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
{
"outlook_multi_mailbox": {
"command": "node",
"args": [
"${CODEX_PLUGIN_ROOT}/dist/plugin/stdio.js"
]
}
}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.
- 10d ago First seen · 8 lines scan A df97a078c579
outlook_multi_mailbox is an MCP server published in the GitHub repository ftaricano/mcp-outlook (2 stars, last pushed 3d 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
iris
A Microsoft 365 mail MCP server that can draft but cannot send. The token has no Mail.Send scope. Runs locally from the iris-mcp Python package. Needs 4 environment variables to run.
outlook-mcp
MCP server for Microsoft Outlook via Microsoft Graph API. Runs locally from the outlook-graph-mcp Python package.
mailwarden
Native Gmail MCP server: search, labels, archive, trash, attachments, and snooze. Runs locally from the mailwarden npm package. Needs 4 environment variables to run.
mcp-server-imap
Email tools for any IMAP/SMTP provider: list, read, search, send, and manage messages. Runs locally from the @aiwerk/mcp-server-imap npm package. Needs 6 environment variables to run.
readndraft
MCP server "readndraft" as configured in LeoPhoenixT/readNdraft-imap-mcp. Launched with uv tool run [email protected] mcp.
mcp-one
Model Context Protocol (MCP) server for one.com mailboxes. Full email management (IMAP/SMTP) for Claude and AI agents. Runs locally from the @xtnd-dynamics/mcp-one npm package.