Skip to main content
Glama
Sign In
proton-bridge-mcp

proton-bridge-mcp

by Considus
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Poll for new mail

poll_folder

Polls a Proton Mail folder for messages that arrived since the last checkpoint, without marking them read. Use advance=false to preview and commit the returned checkpoint to advance safely.

Instructions

Messages that have arrived since the last poll. The very first poll emits nothing and just records where the mailbox ends, so turning this on does not replay the backlog. Marks nothing as read. Pass commit to commit a checkpoint an advance=false poll returned; repeating that is harmless.

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": "poll_folder"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost per call, 1 to 100 (default 20).
commitNoA checkpoint '<uidvalidity>:<uid>', exactly as an advance=false poll reported it. Commits it instead of polling.
folderNoDefault INBOX.
advanceNoDefault true. Set false to look without committing, then confirm with commit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.0.0
    • changedInput schema / properties / advance / description
      Previous value: -"Default true. Set false to look without committing, then confirm with ack_folder."New value: +"Default true. Set false to look without committing, then confirm with commit."
    • addedInput schema / properties / commit
      Added value: +{
+  "description": "A checkpoint '<uidvalidity>:<uid>', exactly as an advance=false poll reported it. Commits it instead of polling.",
+  "type": "string"
+}
  2. First observedv1.2.1

TDQS

A3.9/5.0
Behavior4/5

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

With readOnlyHint=false and idempotentHint=false already declared, the description adds real value: 'Marks nothing as read' clarifies the mutation is limited to a checkpoint, and the first-poll no-backlog rule is a non-obvious behavior an agent would otherwise misjudge. It could go further on what happens if the poll fails mid-advance, but the core side-effect model is disclosed.

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?

Four short, dense sentences with no filler, front-loading the returned data before the caveats. The opening is a noun fragment rather than a verb statement, which is a minor structural weakness but costs no clarity.

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 four-parameter, zero-required, no-output-schema tool, the description covers the mutation model, checkpoint workflow and first-call edge case adequately. It never says what a returned 'message' contains (headers, ids, body) or how checkpoint strings appear in normal poll results, which is the remaining gap given there is no output schema.

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 coverage is 100%, so the schema already documents limit, commit, folder and advance in detail. The description reinforces the advance/commit relationship and notes that repeating commit is harmless, but adds little beyond what the parameter descriptions already state.

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?

The opening line plus title make clear this returns only messages that arrived since the previous poll, which is a distinct incremental-fetch scope an agent can recognize. It never names a sibling (search_mail, get_headers) to contrast with, so differentiation is implicit rather than stated.

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?

It gives concrete usage context: the first poll deliberately returns nothing to avoid replaying the backlog, and the advance=false → commit two-step pattern is spelled out. It stops short of naming when to prefer search_mail or get_headers instead, so the 'when-not' half is missing.

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