VMail MCP

Overview Schema Source Related Servers Discussions Admin

imap_search_emails

Search emails by sender, recipient, subject, body, or date range to find messages when you know details but not the UID. Optionally scan all folders or include message bodies.

Instructions

Note: on some servers a 'flagged' or starred message carries a custom keyword (e.g. an Open-Xchange color label or Apple's $MailFlagBit*) instead of, or in addition to, the \Flagged system flag. After any flagged search, inspect each result's customKeywords field before concluding a message is or isn't flagged — do not rely on the flagged filter alone. Search for emails matching criteria (sender, recipient, subject, body text, date range, read/flagged status). Use this to FIND messages when you know something about them but not their UID — e.g. "emails from amazon last week", "unread invoices". By default searches a single folder (INBOX). Set searchAllFolders=true to scan every mailbox at once — this catches messages filed away by rules (e.g. a receipt routed to a custom folder); Trash/Spam/Drafts are skipped unless you opt in. By default returns lightweight headers (uid, from, subject, date, and folder when searching across folders); set includeBody=true to also return the parsed body in one round-trip instead of paying the N+1 cost of calling imap_get_email per match. For the newest messages without criteria, prefer imap_get_latest_emails.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`to`	No	Search by recipient
`body`	No	Search in body text
`from`	No	Search by sender
`seen`	No	Filter by read/unread status
`limit`	No	Maximum number of results
`since`	No	Search emails since date (YYYY-MM-DD)
`before`	No	Search emails before date (YYYY-MM-DD)
`folder`	No	Folder name to search (default: INBOX). Ignored when searchAllFolders is true.	INBOX
`flagged`	No	Filter by flagged status
`subject`	No	Search by subject
`keywords`	No	Match messages that have ANY of these CUSTOM keywords (server-side OR; not system flags like \Seen/\Flagged). Read a mailbox's available custom keywords from imap_folder_status's customKeywords field, then pass the ones you want here.
`accountId`	No	Account ID (from imap_list_accounts). Optional if accountName is given or only one account is configured.
`messageId`	No	Search by RFC822 Message-ID header (substring match)
`bodyFormat`	No	How to render the body when `includeBody` is true. Mirrors `imap_get_email` — "markdown" (default) returns clean Markdown and omits raw HTML so it never crosses the MCP boundary; "text" returns plain text; "html" returns raw HTML; "auto" prefers substantive text/plain, else Markdown.	markdown
`unKeywords`	No	Exclude messages that have ANY of these CUSTOM keywords (server-side; result has NONE of them). Same keyword source as `keywords` — check imap_folder_status first.
`accountName`	No	Account name instead of accountId. Optional if accountId is given or only one account is configured.
`includeBody`	No	If true, also fetch the parsed message body in the same round-trip and return it alongside headers (avoids the N+1 cost of calling imap_get_email per match). Body is rendered per `bodyFormat` and capped at `bodyMaxLength` characters per field. Off by default to preserve lightweight behavior.
`includeSpam`	No	When searchAllFolders is true, also search Spam/Junk folders (off by default — noisy).
`includeTrash`	No	When searchAllFolders is true, also search Trash/Bin/Deleted folders (off by default — noisy).
`bodyMaxLength`	No	Per-message cap (in characters) for each rendered body field when `includeBody` is true. Defaults to 10000 to match `imap_get_email`.
`includeDrafts`	No	When searchAllFolders is true, also search the Drafts folder (off by default).
`searchAllFolders`	No	Search across ALL folders instead of just `folder`. Skips Trash/Spam/Drafts and non-selectable folders by default. Use when a message might have been filed/archived/moved and you do not know which folder it is in.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 19, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations present, the description carries the full burden, and it delivers: it warns about the flagged/custom-keyword pitfall, explains that Trash/Spam/Drafts are skipped unless opted in, clarifies that lightweight headers are returned by default, and documents body rendering behavior. This goes well beyond a simple 'search emails' statement.

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 description is long but dense with valuable information, and it is structured around key behaviors, defaults, and alternatives. However, it opens with a caveat about flagged searches before stating the tool's core purpose, which slightly delays the main 'what does this do' message. Each sentence earns its place, but the front-loading could be tighter.

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?

For a tool with 22 optional parameters and no output schema, the description provides a thorough operational picture: default folder, return fields, body inclusion trade-offs, folder exclusions, opt-in flags, and a critical edge case. It covers the essential behaviors an agent needs to invoke the tool correctly and interpret its results.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema: it explains the searchAllFolders behavior, the N+1 rationale for includeBody, how keywords relate to imap_folder_status customKeywords, and the flagged-filter caveat. This is genuinely actionable guidance, not a restatement of parameter names.

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 the verb and resource: 'Search for emails matching criteria' and lists concrete filters like sender, recipient, subject, body, date range, and read/flagged status. It also ties the tool to a specific use case — finding messages when you know something about them but not their UID — and distinguishes it from imap_get_latest_emails.

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

Usage Guidelines5/5

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

The description explicitly says when to use this tool ('Use this to FIND messages when you know something about them but not their UID') and when to prefer a sibling ('For the newest messages without criteria, prefer imap_get_latest_emails'). It also gives practical guidance on searchAllFolders for messages filed away by rules and on includeBody to avoid the N+1 cost of calling imap_get_email per match.

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

imap_search_emails

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools