Skip to main content
Glama
MadLlama25

Fastmail MCP Server

by MadLlama25

advanced_search_metadata

Search emails by sender, recipient, subject, date, and more, returning only metadata such as id, subject, and sender. Ideal for privacy-sensitive applications where body content must not be exposed.

Instructions

Same filter capabilities as advanced_search (single-mailbox scoping via mailboxId, multi-mailbox intersection via requiredMailboxIds, exclusion via excludeMailboxIds, plus sender / recipient / subject / free text / date / attachment / unread / pinned) but returns ONLY metadata on each match — id, threadId, subject, from, to, cc, replyTo, receivedAt, hasAttachment, keywords. Does NOT return preview or any body-derived content. Use in privacy-sensitive flows where the routing decision is made from headers alone — for example, when classifying customer mail by sender / recipient / subject / thread state without ingesting body content. The free-text query still searches body content on the server side; only the result envelope comes back without body excerpts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoFilter by recipient email
fromNoFilter by sender email
afterNoEmails after this date (ISO 8601)
limitNoMaximum results (default: 50)
queryNoText to search for in subject/body
beforeNoEmails before this date (ISO 8601)
subjectNoFilter by subject
isPinnedNoFilter pinned emails
isUnreadNoFilter unread emails
ascendingNoSort oldest first instead of newest first (default: false)
mailboxIdNoSearch within a single mailbox. For an intersection across multiple mailboxes (e.g. Inbox AND a label folder), use requiredMailboxIds instead.
hasAttachmentNoFilter emails with attachments
excludeMailboxIdsNoExclude emails that are members of ANY of these mailbox IDs (maps to JMAP inMailboxOtherThan). Useful for queries like "in a parent label but not its archive sub-folder". Combines cleanly with mailboxId / requiredMailboxIds.
requiredMailboxIdsNoRequire membership in ALL of these mailbox IDs (intersection / AND semantic). Use this for queries like "in Inbox AND a label folder" — pass both mailbox IDs in the array. If mailboxId is also passed, it is folded into the intersection (de-duplicated). JMAP cannot express multi-mailbox membership in a single FilterCondition, so this builds a FilterOperator AND over multiple inMailbox conditions on the server.
Behavior4/5

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

No annotations are provided, so the description carries full burden. It clearly states what is returned (metadata) and what is not (preview or body-derived content). It also discloses that free-text query searches body server-side, which is a non-obvious behavior. It lacks details on rate limits or auth, but overall is quite transparent.

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?

The description is efficient, front-loading the key distinction (returns only metadata). Every sentence earns its place: it lists capabilities, return fields, privacy use case, and a behavioral caveat. No wasted words, well-structured.

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?

Given the high number of sibling tools and 14 parameters, the description covers purpose, return value, usage guidance, and filtering details adequately. It doesn't address error handling or edge cases, but for a search tool this is sufficient. The absence of output schema is compensated by listing returned fields.

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 description coverage is 100%, baseline 3. The description adds extra context: explains the difference between mailboxId (single) and requiredMailboxIds (intersection), describes excludeMailboxIds usage, and notes that requiredMailboxIds builds a FilterOperator AND. This adds value beyond the schema.

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?

The description clearly states it returns ONLY metadata (id, threadId, subject, etc.) and distinguishes from advanced_search which presumably returns full content. The phrase 'Same filter capabilities as advanced_search' orients the agent to its sibling, and the explicit list of returned fields makes the purpose unambiguous.

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?

The description gives explicit usage guidance: 'Use in privacy-sensitive flows where the routing decision is made from headers alone' with a concrete example. It also warns that free-text queries still search body server-side, preventing misuse. However, it doesn't explicitly state when not to use this tool versus alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MadLlama25/fastmail-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server