Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

search_indexed_emails

Read-only

Search a local SQLite mailbox index offline without opening IMAP connections. Filter by sender, recipient, subject, label, date, or domain to find indexed emails.

Instructions

Search the local SQLite mailbox index (of ALL configured accounts by default; pass account = address or slug to search only one; non-primary ids are prefixed '::') without making any IMAP connection. Supports free-text and field shortcuts inline: from:alice@example.com, to:bob, subject:invoice, label:Archive, domain:acme.com. Use for fast, offline-capable searches when the index is populated. Prefer search_emails when you need live IMAP results or when the index is stale or empty. Prefer this over search_emails when the index is current. Use search_emails if messages were received after the last sync. Each email's attachments are metadata only (id/filename/contentType/size/disposition) — use list_attachments or get_email_by_id for full attachment detail.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoRecipient filter.
fromNoSender filter.
labelNoFolder or label filter.
limitNoMaximum results.
queryNoFree-text query across indexed metadata.
dateToNoInclusive end date/time in ISO format.
fieldsNoTrim each returned email to just these field names (e.g. ["subject","from","date"]) to save tokens on large result sets. id is always included. Accepts either an array or a comma-separated string. Omit to get the full object.
folderNoFolder filter.
isReadNoRead status filter.
accountNoAccount address or slug to search (see list_accounts). Omit to search ALL configured accounts; non-primary ids come back prefixed '<slug>::'.
subjectNoSubject filter.
dateFromNoInclusive start date/time in ISO format.
threadIdNoThread id filter.
isStarredNoStarred status filter.
mailboxRoleNoNormalized mailbox role like Inbox, Sent, Archive, or Trash.
senderDomainNoSender domain filter such as example.com.
hasAttachmentNoAttachment filter.
attachmentNameNoAttachment filename filter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.43
    • addedInput schema / properties / account
      Added value: +{
+  "description": "Account address or slug to search (see list_accounts). Omit to search ALL configured accounts; non-primary ids come back prefixed '<slug>::'.",
+  "type": "string"
+}
  2. Changed1 schema field changedv2.1.37
    • changedInput schema / properties / limit / default
      Previous value: -100New value: +50
  3. Changed4 schema fields changedv1.17.1
    • changedInput schema / properties / fields / description
      Previous value: -"Trim each returned email to just these field names (e.g. [\"subject\",\"from\",\"date\"]) to save tokens on large result sets. id is always included. Also accepts a comma-separated string. Omit to get the full object."New value: +"Trim each returned email to just these field names (e.g. [\"subject\",\"from\",\"date\"]) to save tokens on large result sets. id is always included. Accepts either an array or a comma-separated string. Omit to get the full object."
    • removedInput schema / properties / fields / items
      Removed value: -{
-  "type": "string"
-}
    • addedInput schema / properties / fields / oneOf
      Added value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "string"
+  }
+]
    • removedInput schema / properties / fields / type
      Removed value: -"array"
  4. Changed1 schema field changedv1.17.0
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Trim each returned email to just these field names (e.g. [\"subject\",\"from\",\"date\"]) to save tokens on large result sets. id is always included. Also accepts a comma-separated string. Omit to get the full object.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  5. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Beyond readOnlyHint, it discloses that no IMAP connection is made, that results are offline/index-derived, that attachments are metadata-only stubs with a pointer to list_attachments/get_email_by_id, and that non-primary account ids come back prefixed '<slug>::'. This is real behavioral context, though return shape and pagination/limit behavior are not discussed.

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?

Front-loaded with the core purpose and the no-IMAP constraint, with the fallback guidance in the middle and the attachment caveat last. Slightly redundant — three consecutive sentences restate the search_emails-vs-index preference — but every sentence carries operational 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?

For an 18-parameter, zero-required, output-schema-less search tool, the description covers the key ambiguities an agent would hit: account scoping, id prefixing, inline query syntax, and the attachment metadata limitation. It stops short of describing result ordering or how staleness is detected, which would be the remaining gaps.

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 is 3, but the description adds meaning the schema does not: inline field-shortcut syntax (from:, to:, subject:, label:, domain:) usable inside the free-text query, and the account/prefix semantics for cross-account search. That is genuinely additive over the structured params.

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 resource — searching the local SQLite mailbox index — and immediately names what it is not: a live IMAP search. An agent can distinguish it from search_emails without opening either schema.

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?

Gives explicit when-to-use routing: prefer this when the index is current, prefer search_emails when live IMAP results are needed or the index is stale/empty, and use search_emails for messages received after the last sync. The condition that selects each alternative is spelled out.

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