proton-bridge-mcp

Overview Schema Source Related Servers Discussions Admin

Search a folder

search_mail

Read-only

Search Proton Mail folders or all mailboxes by text, sender, subject, date, unread or flagged status; get newest messages first with optional label and folder locations.

Instructions

Search a folder. Combine any of: text, from, subject, since (DD-Mon-YYYY), unread_only, flagged_only. Returns uids + envelopes, newest first. With no filters it lists the newest messages in the folder. Set include_locations to also report which labels and folders each message carries. Set all_folders to search every mailbox at once when you do not know where something is: duplicates collapse by Message-ID and each row says where the message lives.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_mail"
  }
}

Input Schema

Name	Required	Description
`from`	No
`text`	No
`limit`	No	Max results (default 15, or the most recent 25 with all_folders).
`since`	No	DD-Mon-YYYY, e.g. 01-Jul-2026
`before`	No	DD-Mon-YYYY. Combine with since for a date range.
`folder`	No	Folder to search, e.g. INBOX, 'All Mail', 'Folders/<name>'. Default INBOX.
`subject`	No
`all_folders`	No	Search every mailbox instead of one folder. Takes no folder, uidvalidity or include_locations.
`uidvalidity`	No	UIDVALIDITY reported alongside the uid. Pass it back so a mailbox resync cannot make this act on the wrong message.
`unread_only`	No
`flagged_only`	No
`include_locations`	No	Report every other mailbox each message appears in, so you can tell what it is already labelled or filed as without a second search. Costs one search per mailbox.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv2.0.0Oct 24, 2026

addedInput schema / properties / all_folders

Added value: +{
+  "description": "Search every mailbox instead of one folder. Takes no folder, uidvalidity or include_locations.",
+  "type": "boolean"
+}

changedInput schema / properties / limit / description

Previous value: -"Max results (default 15)."New value: +"Max results (default 15, or the most recent 25 with all_folders)."

First observedv1.2.1Aug 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real behavioral context beyond that — result ordering, no-filter default, Message-ID de-duplication across mailboxes, and an explicit cost note that include_locations runs one search per mailbox. It stops short of describing bounding behavior for large result sets outside the limit parameter.

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?

Four sentences, no filler, purpose and filter list front-loaded, then return shape, then default behavior, then the two opt-in switches with their consequences. Every sentence carries information an agent needs to choose or configure the call.

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 12-parameter, zero-required search tool with no output schema, the description covers what matters: how to combine filters, what an empty filter set does, what comes back and in what order, and what the expensive options do. No output schema exists but the return shape is stated in prose, so nothing essential is missing.

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 58%, and the description compensates by enumerating the combinable filters (text, from, subject, since with DD-Mon-YYYY, unread_only, flagged_only) and by explaining the two highest-risk switches. The four undocumented-in-schema parameters are the self-evident string/boolean filters, so the gap is minor; limit and before are left entirely to the schema.

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?

States a specific verb and resource ("Search a folder") and immediately grounds it with the combinable filter set and return shape (uids + envelopes, newest first). It does not name or differentiate itself from the closest sibling, find_thread, so an agent must infer which search entry point applies.

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 clear conditional guidance: no filters means list the newest messages, and use all_folders "when you do not know where something is." No exclusions or prerequisites are stated against alternatives such as find_thread or poll_folder.

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