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 agentmods add skills/superhuman/mcp-mail/superhuman-mailnpx skills add superhuman/mcp-mail --skill superhuman-mailgit clone --depth 1 https://github.com/superhuman/mcp-mailWrote 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/superhuman/mcp-mail/superhuman-mail)<a href="https://agentmods.dev/skills/superhuman/mcp-mail/superhuman-mail"><img src="https://agentmods.dev/badge/skills/superhuman/mcp-mail/superhuman-mail.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00409 |
| Opus 5 | $0.00022 | $0.00204 |
| Sonnet 5 | $0.00009 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
superhuman-mail 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 6d 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
Superhuman Mail
Use the superhuman-mail MCP server whenever the user asks to work with Superhuman Mail, their inbox, email threads, drafts, sending, read statuses, labels, Split Inboxes, availability, or calendar events.
Workflow
- Use the MCP server's advertised tool descriptions as the source of truth. Tool names may evolve server-side.
- For sensitive reads such as inbox search, message retrieval, calendar lookup, contacts, or attachments, proceed only when the user's request clearly authorizes that read.
- For write or destructive actions such as sending mail, trashing threads, unsubscribing, updating labels, updating personalization, or creating calendar events, summarize the intended action and get user confirmation before calling the tool unless the user has already explicitly approved that exact action.
- Prefer creating or updating drafts before sending when the user's intent is ambiguous.
- When multiple mail accounts are connected, ask which account to use unless the prompt identifies it.
Common Capabilities
The official Superhuman Mail MCP server can support workflows such as:
- Search email and calendar with natural language.
- List and fetch email threads and messages.
- Create, update, discard, and send drafts.
- Get attachments and read statuses.
- List labels and Split Inboxes.
- Update threads by labeling, starring, marking read or done, moving to or from Trash, and similar mailbox actions.
- Create or update events and find availability.
- Update personalization used for drafting and event creation.
Safety Notes
Superhuman Mail MCP is a remote server hosted by Superhuman. Email and calendar data returned by MCP tools is sent back to the AI client so the model can reason over it. Be especially explicit before using tools that send emails instantly or expose message contents.
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.
- 6d ago First seen · 34 lines · 44 tokens per session scan A 3d7ac797d104
superhuman-mail is a skill published in the GitHub repository superhuman/mcp-mail (28 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 409 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.