macos-mail-mcp

Overview Schema Source Related Servers Discussions Admin

read_attachment

Reads valid UTF-8 email attachment text inline so you can inspect supported text, JSON, XML, YAML, CSV, HTML, Markdown, or log files without saving them.

Instructions

Read valid UTF-8 attachment text inline. Accepts text/*, application/json, application/xml, application/x-yaml MIME types or .txt, .csv, .json, .html, .md, .xml, .log extensions. Uses extension-based MIME fallback when unavailable. Use save_attachment for binary files.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "messageId": "<messageId>",
      "mailboxName": "<mailboxName>",
      "accountName": "<accountName>",
      "attachmentName": "<attachmentName>"
    },
    "name": "read_attachment"
  }
}

Input Schema

Name	Required	Description
`messageId`	Yes	The numeric ID of the message
`accountName`	Yes	The name of the account containing the mailbox
`mailboxName`	Yes	The name of the mailbox containing the message
`attachmentName`	Yes	The name of the attachment to read

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.3.2Aug 21, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / messageId / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / messageId / minimum
```
Added value: +-9007199254740991
```
First observedv1.2.0Jun 21, 2026

TDQS

A4/5.0

Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden. It does useful work — declaring UTF-8-only decoding, the accepted MIME/extension set, and extension-based MIME fallback — but says nothing about what happens when the type is unsupported, whether content is truncated or size-limited, or what the response looks like (no output schema exists).

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

Conciseness5/5

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

Three tight sentences with zero filler: capability first, accepted inputs second, alternative tool last. The routing hint is placed where an agent scanning for alternatives will find it.

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

Completeness4/5

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

For a simple read tool with full schema coverage and no output schema, the description covers the essential decision inputs: what qualifies as readable and where to go otherwise. The remaining gap is error/edge-case behavior for unsupported attachments, which is minor but not trivial given there is no output schema to explain returns.

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

Parameters3/5

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

Schema description coverage is 100%, with all four required parameters individually documented (messageId, accountName, mailboxName, attachmentName). The description adds no parameter-level meaning such as whether attachmentName is a path, display name, or identifier, so the baseline of 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('Read ... attachment text inline') plus the content constraints (valid UTF-8) that define the operation. It also explicitly names the sibling it is not ('Use save_attachment for binary files'), so an agent can separate the two without inspecting schemas.

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?

Gives a clear routing rule: text MIME types and listed extensions go here, binary files go to save_attachment. It enumerates exactly which inputs qualify, but does not say what to do with attachments that fall in neither bucket (e.g., an unlisted text-like extension) or how to discover attachments in the first place.

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