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.
npx skills add CeDJeY/mailpit-mcp-server --skill route-mail-to-mailpitgit clone --depth 1 https://github.com/CeDJeY/mailpit-mcp-serverWrote 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/skills/cedjey/mailpit-mcp-server/route-mail-to-mailpit)<a href="https://agentmods.dev/skills/cedjey/mailpit-mcp-server/route-mail-to-mailpit"><img src="https://agentmods.dev/badge/skills/cedjey/mailpit-mcp-server/route-mail-to-mailpit/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/skills/cedjey/mailpit-mcp-server/route-mail-to-mailpit"><img src="https://agentmods.dev/badge/skills/cedjey/mailpit-mcp-server/route-mail-to-mailpit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00875 |
| Opus 5 | $0.00032 | $0.00438 |
| Sonnet 5 | $0.00013 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
route-mail-to-mailpit 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route application email to Mailpit
Mailpit only captures what is sent to its SMTP port. Before any email verification can work, the application under test must be configured to send there — and you must prove it, not assume it.
Two different addresses — don't confuse them
- SMTP host:port — where the application sends mail (e.g.
mailpit-host:1025; deployments often remap the port). No TLS, credentials optional (accepted but ignored). - MCP endpoint URL — where you (the agent) read the mailbox (e.g.
http://mailpit-host:3000/mcp). Never give this to the application.
First call get_mailbox_info: SMTPEndpoint is the authoritative answer — the operator configured exactly where applications must send for THIS mailbox to capture their mail. Compare the project's mail config against it; any other destination (a different Mailpit instance, a real provider) means verification will wait for emails that never arrive here. Do not derive the SMTP port from the MCP URL — they are unrelated.
Prove the mailbox side before debugging the app side: send_smtp_message performs a real SMTP transaction to the endpoint (like an application would) — if it lands (confirm with wait_for_message), the SMTP channel works and any remaining problem is in the app's configuration. If the endpoint names an address unreachable from the MCP server's own network (e.g. localhost:...), pass the tool's endpoint parameter with a network-local address (such as the Mailpit container hostname mailpit:1025) — that still proves Mailpit accepts SMTP, though not the app-visible path.
Configure the application
Find where the app defines its outgoing mail transport and point it at Mailpit — typical spots: SMTP_HOST/SMTP_PORT/MAIL_HOST env vars, Laravel MAIL_*, Django EMAIL_HOST, Rails smtp_settings, Spring spring.mail.*, nodemailer transport options. Set: Mailpit's host and SMTP port, TLS off (or STARTTLS optional), any or no credentials.
Safety check — do this even if routing "already works": scan the app's mail config (all environments that tests touch) for real provider hosts — sendgrid, mailgun, ses/amazonaws, postmark, resend, smtp.gmail.com, office365, or any production SMTP relay. If the test environment can reach a real provider, flag it to the user immediately: test runs could email real people. Verification must never run against a configuration that might deliver externally.
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.
- 11d ago First seen · 36 lines · 65 tokens per session scan A 67c4786e7479
route-mail-to-mailpit is a skill published in the GitHub repository CeDJeY/mailpit-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 875 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.