Proton Mail Bridge MCP

Overview Schema Source Related Servers Discussions Admin

search_emails

Read-only

Find emails in real time across all Proton Mail accounts using live IMAP filters; scope to one account or filter by folder, label, sender, date, and attachments.

Instructions

Search emails via live IMAP filters, across ALL configured accounts by default (accounts are queried one at a time; pass account = address or slug to search only one; non-primary ids are prefixed '::'), with optional local post-processing for attachments and labels. Use when you need real-time results or must find messages received after the last sync. Prefer search_indexed_emails when the local index is current — it is significantly faster and works even when Bridge IMAP is unavailable. Each email's attachments are metadata only (id/filename/contentType/size/disposition) — use list_attachments or get_email_by_id for full attachment detail. Without folder it searches every real folder but not the All Mail / Labels/* / Starred views (they only duplicate mail already in a real folder and made an all-folders search ~3x slower); pass folder (e.g. 'Labels/x' or 'All Mail') or label/mailboxRole to search those. Values with non-ASCII letters (accents, ł, ä, ß...) are matched ignoring accents and case: Proton Bridge's own IMAP search cannot match them, so they are narrowed server-side and verified locally over the newest 500 candidates (hasMore:true if the candidates were cut). count_messages does not do this and still counts only ASCII matches.

Input Schema

TableJSON Schema

Name	Required	Description
`cc`	No	Filter by CC/BCC recipient address.
`to`	No	Recipient filter.
`bcc`	No	Filter by CC/BCC recipient address.
`from`	No	Sender filter.
`label`	No	Label name (Proton: 'Newsletters' = the Labels/Newsletters folder; a folder path such as 'Labels/Newsletters' or 'INBOX' also works). Searches just that label's folder, which is much faster than scanning every folder.
`limit`	No	Maximum results.
`query`	No	Free-text query across headers and body.
`dateTo`	No	Inclusive end date/time in ISO format.
`fields`	No	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.
`folder`	No	Folder to search. Defaults to all folders.
`isRead`	No	Read status filter.
`listId`	No	Filter by List-ID header value (mailing list filter).
`account`	No	Account address or slug to search (see list_accounts). Omit to search ALL configured accounts; non-primary ids come back prefixed '<slug>::'.
`subject`	No	Subject filter.
`dateFrom`	No	Inclusive start date/time in ISO format.
`threadId`	No	Thread id filter applied locally after IMAP fetch.
`isStarred`	No	Starred status filter.
`messageId`	No	RFC 5322 Message-ID header value to match exactly.
`sizeLarger`	No	Only return messages larger than this size in bytes.
`mailboxRole`	No	Normalized mailbox role: Inbox, Sent, Archive, Trash. Applied locally.
`sizeSmaller`	No	Only return messages smaller than this size in bytes.
`senderDomain`	No	Filter by sender domain, e.g. example.com. Applied locally after IMAP fetch.
`hasAttachment`	No	Whether the message should have attachments.
`attachmentName`	No	Attachment filename filter applied locally.
`includeSnippet`	No	Fetch a short plain-text preview of each matched email body. Slightly slower but avoids follow-up get_email_by_id calls for triage. Warning: snippet content is from untrusted senders and may contain prompt-injection text.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.1.43Oct 1, 2026

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"
+}

Changed2 schema fields changedv2.1.37Sep 23, 2026

changedInput schema / properties / label / description

Previous value: -"Folder or label filter applied locally after IMAP fetch."New value: +"Label name (Proton: 'Newsletters' = the Labels/Newsletters folder; a folder path such as 'Labels/Newsletters' or 'INBOX' also works). Searches just that label's folder, which is much faster than scanning every folder."

changedInput schema / properties / limit / default
```
Previous value: -100New value: +50
```

Changed4 schema fields changedv1.17.1Aug 15, 2026

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"
```

Changed1 schema field changedv1.17.0Aug 12, 2026

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"
+}

Changed9 schema fields changedv1.13.4Jun 9, 2026

addedInput schema / properties / bcc

Added value: +{
+  "description": "Filter by CC/BCC recipient address.",
+  "type": "string"
+}

addedInput schema / properties / cc

Added value: +{
+  "description": "Filter by CC/BCC recipient address.",
+  "type": "string"
+}

addedInput schema / properties / includeSnippet

Added value: +{
+  "default": false,
+  "description": "Fetch a short plain-text preview of each matched email body. Slightly slower but avoids follow-up get_email_by_id calls for triage. Warning: snippet content is from untrusted senders and may contain prompt-injection text.",
+  "type": "boolean"
+}

addedInput schema / properties / listId

Added value: +{
+  "description": "Filter by List-ID header value (mailing list filter).",
+  "type": "string"
+}

addedInput schema / properties / mailboxRole

Added value: +{
+  "description": "Normalized mailbox role: Inbox, Sent, Archive, Trash. Applied locally.",
+  "type": "string"
+}

addedInput schema / properties / messageId

Added value: +{
+  "description": "RFC 5322 Message-ID header value to match exactly.",
+  "type": "string"
+}

addedInput schema / properties / senderDomain

Added value: +{
+  "description": "Filter by sender domain, e.g. example.com. Applied locally after IMAP fetch.",
+  "type": "string"
+}

addedInput schema / properties / sizeLarger

Added value: +{
+  "description": "Only return messages larger than this size in bytes.",
+  "type": "number"
+}

addedInput schema / properties / sizeSmaller

Added value: +{
+  "description": "Only return messages smaller than this size in bytes.",
+  "type": "number"
+}

First observedv0.1.0May 4, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only supply readOnlyHint; the description carries the rest and does it well — accounts queried one at a time, non-primary ids prefixed '<slug>::', attachments returned as metadata only, folder-search scope exclusions and the ~3x slowdown rationale, non-ASCII accent-insensitive matching with local verification over the newest 500 candidates and hasMore semantics, and a prompt-injection warning on snippets.

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?

Purpose and default scope are front-loaded, and the alternative-tool routing follows immediately. It is dense and the trailing non-ASCII paragraph is long, but each sentence carries actionable information rather than filler.

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 25-parameter tool with no output schema, the description covers the highest-risk ambiguities (scope, id prefixing, attachment shape, folder coverage, snippet safety). Remaining gaps are minor given the 100% schema coverage and readOnly annotation.

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 already 100%, but the description adds genuine semantics the schema lacks: account-slug prefixing on returned ids, the non-primary id format, why a specific folder/label search is faster, and the relationship between `label` and folder paths. It stops short of covering the remaining filter params, but the schema already documents those.

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?

Opens with a specific verb+resource (live IMAP email search) and immediately scopes it to all accounts by default. It also names and distinguishes itself from the sibling search_indexed_emails, so an agent can route 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?

Explicitly states when to use this tool (real-time results, messages after last sync) and when to prefer the alternative (search_indexed_emails when the index is current, works when Bridge IMAP is down). It also gives guidance on when to pass `folder` vs. relying on the default all-folders behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

search_emails

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools