Skip to main content
Glama
Sign In
proton-mcp

proton-mcp

by RndmJoker
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Set read state and star

set_flags
Idempotent

Marks Proton Mail messages as read or unread and stars or unstars them in one call. Use it to update message status without changing content or mailbox location.

Instructions

Marks messages as read or unread and sets or clears the star. At least one of the two has to be given. This changes nothing about where a message sits and nothing about its content. Proton shows the star as the "Starred" mailbox.

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": {
      "messageIds": "<messageIds>"
    },
    "name": "set_flags"
  }
}

Input Schema

NameRequiredDescriptionDefault
readNoTrue marks the messages as read, false as unread. Omit to leave it alone.
mailboxNoThe mailbox the messages are in, if they share one. Only a shortcut: without it every message is looked for across the mailboxes it could be in, which costs a request each.
starredNoTrue stars the messages, false removes the star. Omit to leave it alone.
messageIdsYesThe message ids, as they came from a listing or a search. At most 50 per call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.11

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description then adds value beyond them by clarifying the non-effects (position and content untouched) and by noting the Proton-side 'Starred' mailbox mapping, which explains an observable side effect of starring. It stops short of saying what happens on error or with unknown ids.

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 short sentences, front-loaded with the action, followed by the invocation constraint, then the scope exclusion. Nothing is padded and every sentence carries information.

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?

With no output schema and full schema coverage, the description needn't explain return values; it does supply the invocation constraint, idempotent semantics and scope exclusion. Only edge-case behaviour (invalid ids, partial failures across 50 messages) is unaddressed.

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 100%, so baseline would be 3, but the description adds a constraint the schema does not encode: only messageIds is required, yet at least one of read/starred must be supplied. That is genuine meaning beyond the structured fields.

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 (marks/sets) plus the exact resource attributes affected (read state and star), and explicitly rules out what neighbours like move_messages do by saying it changes neither location nor content. An agent can distinguish it from add_label/remove_label and move_messages without opening the schema.

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

Usage Guidelines3/5

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

The 'at least one of the two has to be given' constraint tells the caller the minimum viable invocation, and the no-move/no-content-changes sentence implies the scope. But there is no explicit guidance on when to prefer this over siblings such as add_label or move_messages, so usage is only implied.

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