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 arkaigrowth/gmail-mcp-server --skill gmail-multigit clone --depth 1 https://github.com/arkaigrowth/gmail-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/arkaigrowth/gmail-mcp-server/gmail-multi)<a href="https://agentmods.dev/skills/arkaigrowth/gmail-mcp-server/gmail-multi"><img src="https://agentmods.dev/badge/skills/arkaigrowth/gmail-mcp-server/gmail-multi/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/arkaigrowth/gmail-mcp-server/gmail-multi"><img src="https://agentmods.dev/badge/skills/arkaigrowth/gmail-mcp-server/gmail-multi.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 | $0.00044 | $0.00688 |
| Opus 5.5 | $0.00018 | $0.00275 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
gmail-multi 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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Multi
Use this skill when working through the local gmail-multi MCP server. Treat the MCP server as the durable contract: it supports multi-account routing, Keychain token storage, safe modify actions, draft-first sending, and explicit confirmation for irreversible-feeling actions.
Core Rules
- Prefer
gmail_search_emailsfirst for mailbox analysis. It returns message metadata, snippets,nextPageToken, andresultSizeEstimate. - Shortlist from search results before reading bodies. Use
gmail_batch_read_messagesonly when snippets are insufficient. - Use
gmail_read_threadwhen prior context changes a summary, reply, recipient choice, or urgency classification. Usemax_messagesfor long threads. - Always state account, query/timeframe, result coverage, and whether bodies or full threads were read.
- Treat "needs reply" as an inference from content and thread state, not a guaranteed Gmail signal.
- Never use direct Gmail send. Create or update drafts, then stage send with
gmail_send_draft, then confirm withgmail_confirm_sendonly after explicit user approval. - Use
html_bodyplus a plain-textbodyfallback when a draft needs Gmail-safe rich rendering for code, JSON, compact tables, or other formatting. - For labels/archive/trash, prefer explicit message IDs. Query-based bulk labeling must go through preview and confirmation.
Reference Workflows
- Search, pagination, and body-read strategy: references/search-workflow.md
- Inbox triage and action buckets: references/inbox-triage-workflow.md
- Reply, draft, and forwarding workflow: references/reply-draft-workflow.md
- Label, archive, trash, and bulk safety: references/label-archive-safety-workflow.md
Tool Map
- Search/read:
gmail_search_emails,gmail_batch_read_messages,gmail_read_message,gmail_read_thread - Draft/send:
gmail_create_draft,gmail_list_drafts,gmail_update_draft,gmail_send_draft,gmail_confirm_send - Forward:
gmail_create_forward_draft - Organize:
gmail_create_label,gmail_apply_labels_to_messages,gmail_archive_messages - Two-step destructive cleanup:
gmail_stage_trash_messages,gmail_confirm_trash_messages - Query bulk labeling:
gmail_prepare_bulk_label_query,gmail_confirm_bulk_label_operation - Workspace read:
drive_search_docs,drive_get_file_metadata,docs_read_document,drive_list_comments,drive_list_revisions - Workspace write:
drive_create_folder,drive_upload_file,drive_create_text_doc
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 42 lines · 44 tokens per session scan A e929491bea0d
gmail-multi is a skill published in the GitHub repository arkaigrowth/gmail-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 688 once invoked, about $0.0002 per session on Opus 5.5. 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
mailbridge
Work safely with email accounts configured in macOS Mail through the Mailbridge MCP tools. Use when an assistant needs to list Mail accounts or mailboxes, search or read messages and attachments, change read or flagged state, create drafts, preview outbound mail, or explicitly send an approved attachment-free message…
triage
Work a Gmail inbox with mailwarden — search, bulk actions, snooze, unsubscribe and recurring checks, with the rules that keep a bulk action from touching mail the user never meant to touch. Use when the user asks to triage, clean up, archive, label, snooze or unsubscribe from mail through mailwarden, before any…
apple-notes-search
Search, recall, and discover connections across the user's own Apple Notes via the apple-notes MCP server — semantic + keyword search, Swanson-ABC bridges, entity threads, related-notes, and cited synthesis over everything they've ever written. Use AGGRESSIVELY whenever the user wants to find, recall, look up, or…
onlyswitch-deeplink
Invoke OnlySwitch built-in switches or buttons via deeplink. Use when the user asks to toggle or trigger an OnlySwitch action (e.g. empty trash, keep awake, dark mode, mute, hide desktop, clear clipboard, eject discs, Xcode derived data, and any other built-in switch or button). Resolve the request to the correct…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
gmail-trigger
Beta. Act on new Gmail as it arrives: get pinged only for urgent mail, digest newsletters, forward invoices — any standing instruction, across one or several accounts.