Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

bulk_update_flags

Apply or remove IMAP flags (e.g. \Seen, \Flagged) to multiple messages at once using explicit IDs or search criteria. Handles skipped flags per message.

Instructions

Add or remove IMAP flags on multiple messages simultaneously. Prefer update_message_flags for a single message when you need per-flag server verification. Use when the same flag change (e.g. \Seen, \Flagged) should apply to several messages. Accepts emailIds[] OR match+folder (XOR). Returns notApplied[] per message for flags the server silently dropped. \Seen/\Flagged/\Deleted are gated the same as mark_email_read/star_email/bulk_delete: each requires the matching action in PROTONMAIL_ALLOWED_ACTIONS, and setting \Deleted also requires confirmed:true when PROTONMAIL_CONFIRM_DESTRUCTIVE is enabled.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
matchNoSearch criteria. XOR with emailIds.
dryRunNo
folderNoSource folder (required with match).
emailIdsNoExplicit email IDs. XOR with match.
confirmedNoPass true to confirm setting \\Deleted. Required when PROTONMAIL_CONFIRM_DESTRUCTIVE is enabled.
flagsToAddNoIMAP flags to set, e.g. ["\\Seen", "\\Flagged"].
maxBatchSizeNoMaximum number of messages to process. Defaults to 500. Use to prevent runaway operations.
flagsToRemoveNoIMAP flags to clear.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.37
    • addedInput schema / properties / confirmed
      Added value: +{
+  "description": "Pass true to confirm setting \\\\Deleted. Required when PROTONMAIL_CONFIRM_DESTRUCTIVE is enabled.",
+  "type": "boolean"
+}
  2. Addedv1.17.0
  3. Removedv1.13.11
  4. Addedv1.13.4

TDQS

A3.8/5.0
Behavior1/5

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

The description mentions destructive operations and gating: setting '\Deleted' requires `confirmed:true` under PROTONMAIL_CONFIRM_DESTRUCTIVE and is 'gated the same as ... bulk_delete.' This contradicts the annotation `destructiveHint: false`, which implies the tool is not destructive. Per the rubric, a contradiction forces a score of 1 regardless of other behavioral disclosures.

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 dense sentences cover purpose, alternatives, when to use, parameter mode, return behavior, and permission gating. There is no filler; each sentence earns its place and the most important scoping information is front-loaded.

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 complex 8-parameter bulk operation with no output schema, the description does well: it names the alternative, explains the two invocation modes, discloses the `notApplied[]` return, and covers permission gating. However, it does not explain `dryRun` semantics or the broader success/error return shape, which leaves minor gaps.

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 88%, so the schema already documents most parameters. The description reinforces the XOR relationship between `emailIds` and `match+folder` and the `confirmed:true` requirement, but it does not add substantial meaning beyond what the parameter descriptions already provide. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Add or remove IMAP flags on multiple messages simultaneously.' It clearly differentiates itself from the sibling update_message_flags by noting when that single-message tool is preferable, so an agent can distinguish them without opening schemas.

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?

Explicit guidance is given: 'Prefer update_message_flags for a single message when you need per-flag server verification' and 'Use when the same flag change ... should apply to several messages.' This directly tells the agent when to choose this tool versus an alternative, which is exactly what this dimension asks for.

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