Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

sync_emails

Incrementally import IMAP email metadata into the local SQLite search index, using checkpoints to avoid re-fetching; set full:true to prune moved, archived, or trashed messages.

Instructions

Incrementally sync email metadata from IMAP into the local SQLite index, using stored checkpoints to avoid re-fetching already-indexed messages. Use before calling search_indexed_emails or get_threads when the index may be stale. The default incremental sync only ever adds/updates recent messages — it never notices a message that was archived, trashed, or moved out of the synced folder by any client, so search/thread/digest tools can keep showing a message as still present indefinitely. Set full:true (per folder — sync each folder you want cleaned up) to also detect and prune those, in addition to fetching a larger sample. Prefer run_background_sync to trigger the scheduled sync cycle (also incremental-only by default; see PROTONMAIL_AUTO_SYNC_FULL).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoFetch a larger per-folder sample, and detect/prune messages no longer present in this folder (moved, archived, trashed, or deleted by any client) that the default incremental sync would otherwise leave stale in the index forever.
folderNoFolder to sync. Defaults to all folders.
limitPerFolderNoOverride the per-folder fetch limit.
timeBudgetSecondsNoWall-clock budget for a per-call sync (default 45, max 300). Each folder is committed to the index as soon as it is fetched; when the budget is reached no further folder is started and the response reports complete:false with remainingFolders. Call again to continue (least-recently-synced folders go first).
includeAttachmentTextNoExtract searchable text from text-like attachments while syncing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.43
    • addedInput schema / properties / timeBudgetSeconds
      Added value: +{
+  "default": 45,
+  "description": "Wall-clock budget for a per-call sync (default 45, max 300). Each folder is committed to the index as soon as it is fetched; when the budget is reached no further folder is started and the response reports complete:false with remainingFolders. Call again to continue (least-recently-synced folders go first).",
+  "type": "number"
+}
  2. Changed1 schema field changedv1.18.1
    • changedInput schema / properties / full / description
      Previous value: -"Fetch a larger per-folder sample."New value: +"Fetch a larger per-folder sample, and detect/prune messages no longer present in this folder (moved, archived, trashed, or deleted by any client) that the default incremental sync would otherwise leave stale in the index forever."
  3. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare destructiveHint=false, so the description carries the load and does so: it discloses the non-obvious trap that incremental sync never notices archived/trashed/moved messages, leaving stale index entries visible to search and digest tools indefinitely. It further explains the time-budget commit semantics (per-folder commits, complete:false, remainingFolders, least-recently-synced ordering) that no structured field conveys.

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?

Dense and front-loaded: the first sentence gives the core operation, the second routes usage, the third and fourth explain the critical staleness caveat, the last names the alternative. It is longer than typical but almost every clause carries an operational fact; minor tightening of the long pruning sentence is possible.

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 5-parameter, zero-required mutation-ish tool with no output schema and thin annotations, the description supplies the staleness semantics, per-folder pruning requirement, budget/continuation contract, and sibling alternative. An agent has everything needed to invoke it correctly and to interpret a partial run.

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 the baseline is 3, but the description adds meaning the schema does not: that full is per-folder and must be repeated for each folder to be cleaned, and that full also fetches a larger sample rather than only pruning. timeBudgetSeconds behavior is cross-referenced rather than restated.

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 and dual resource: incrementally sync email metadata from IMAP into a local SQLite index, with the checkpoint mechanism named. It is immediately distinguishable from sibling sync tools like sync_folders, run_background_sync, and sync_draft_to_remote because it names the index and the incremental strategy.

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?

Explicitly says to call it before search_indexed_emails or get_threads when the index may be stale, and names run_background_sync as the scheduled-cycle alternative with its own caveat. It also tells the agent when to use full:true and that it must be applied per folder, which is genuine routing guidance rather than implication.

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