Skip to main content
Glama
sfls1397

Apple Tools MCP

by sfls1397
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

mail_send

Send an email through Mail.app. Success means the message was verified in Sent or is still in Outbox (still sending) — AppleScript send returning is not enough.

Instructions

Send an email through Mail.app. Success means the message was verified in Sent or is still in Outbox (still sending) — AppleScript send returning is not enough. Sending to more than one recipient in total (to + cc + bcc) requires confirm=true. dry_run and unconfirmed multi-recipient calls are not deliveries (MCP isError). A send hang is a timeout, not TCC, unless Mail reports -1743/-10004; hang recover matches To+subject (Message-ID when available), never subject alone. Clients must Sent-check before retrying a timed-out send.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoCC email addresses
toYesRecipient email addresses (required, at least one)
bccNoBCC email addresses
bodyYesMessage body (required)
confirmNoRequired for deletes and multi-recipient sends; without it the call only previews
dry_runNoPreview only: report what would happen and change nothing (default false)
subjectYesSubject line (required)
body_formatNoPlain text (default) or HTML. HTML is tag-stripped; the body is pasted into Mail's compose window (System Events focus on the message body, then Cmd-A and clipboard paste). AppleScript content/html content is not set because it quote-wraps the Sent body
idempotency_keyNoStable unique delivery key. Reuse for retries of the same message; a new key represents a new intended delivery. Without a key identical accepted mail is suppressed without expiry; uncertain sends stay blocked.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.2.3
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Stable unique delivery key. Reuse for retries of the same message; a new key represents a new intended delivery. Without a key identical accepted mail is suppressed without expiry; uncertain sends stay blocked.",
+  "type": "string"
+}
  2. First observedv3.0.8

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so richly: it defines delivery success via Sent/Outbox verification, explains timeout vs TCC behavior, cites specific Mail error codes, and gives retry guidance. This is well beyond what the schema alone provides.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and success definition are front-loaded, and the dense clauses all carry operational information. It is efficient for a behaviorally complex send tool, though the semicolon-heavy phrasing could be easier to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and nine parameters, the description covers the missing behavioral context: success verification, confirmation rules, dry-run behavior, timeout handling, error-code exceptions, and retry safety. An agent has enough information to invoke and retry correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds useful meaning by clarifying that multi-recipient means to + cc + bcc in total and that dry_run or unconfirmed multi-recipient calls are not deliveries, which sharpens the schema's confirm and dry_run semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: send an email through Mail.app. That clearly distinguishes it from drafting or replying tools, but it does not explicitly name the nearest siblings such as mail_draft or messages_send.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operational context for use, including the confirm requirement for multi-recipient sends and that dry_run or unconfirmed multi-recipient calls are not deliveries. It does not explicitly compare this tool to alternatives like mail_draft or mail_reply.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools