Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

create_draft

Save a new outbound email as a local draft, optionally syncing it to Proton Drafts, so you can compose and review before sending.

Instructions

Save a new outbound message as a local draft in SQLite, optionally syncing it to the Proton Drafts IMAP folder. Use to compose and review before sending. Prefer create_reply_draft when replying to a specific emailId, or create_forward_draft when forwarding. Returns a draftId for later update, sync, or send via send_draft.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoCC recipient email addresses, comma-separated.
toNoRecipient email addresses, comma-separated.
bccNoBCC recipient email addresses, comma-separated.
bodyYesDraft body.
fromNoSend as this address instead of the Bridge login's default when the draft is sent (e.g. an alias or additional address on the same Proton account). Proton accepts any address verified on the account; an address not on the account is rejected by Proton at send time.
notesNoOptional local note for the draft.
isHtmlNoWhether the body should be HTML.
replyToNoOptional reply-to email address.
subjectYesDraft subject.
priorityNo
attachmentsNoAttachments with base64 encoded content.
syncToRemoteNoWhether to sync the draft to the Proton Drafts mailbox when IMAP is available.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.37
    • addedInput schema / properties / from
      Added value: +{
      +  "description": "Send as this address instead of the Bridge login's default when the draft is sent (e.g. an alias or additional address on the same Proton account). Proton accepts any address verified on the account; an address not on the account is rejected by Proton at send time.",
      +  "type": "string"
      +}
  2. Addedv1.17.0
  3. Removedv1.13.11
  4. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only provide destructiveHint=false, so the description carries the behavioral disclosure burden. It discloses local SQLite storage, optional sync to Proton Drafts IMAP, and the returned draftId enabling later update, sync, or send. This is useful context beyond the annotations, though it could be slightly more explicit about side effects or failure modes.

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 focused sentences with no fluff. The core behavior, usage guidance, sibling alternatives, and return value are all packed in efficiently.

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 12-parameter tool with high schema coverage, the description explains the workflow, the local vs remote distinction, and the draft lifecycle via draftId. Nothing essential for an agent to invoke it correctly seems missing.

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 description coverage is 92%, so parameters are already well documented. The description does not add significant parameter-level detail, but given the high schema coverage, a baseline of 3 is appropriate.

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?

Description states a specific action (save a new outbound message as a local draft in SQLite) and clearly distinguishes from create_reply_draft and create_forward_draft. An agent can readily understand what this tool does and how it differs from siblings.

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 use this tool for composing and reviewing before sending, and tells the agent to prefer create_reply_draft when replying to a specific emailId and create_forward_draft when forwarding. This provides unambiguous when-to-use guidance.

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