MCP Tools Reference: gmailmcp.googleapis.com

Tool: list_drafts

Lists draft emails from the authenticated user's Gmail account.

This tool can filter drafts based on a query string and supports pagination. It returns a list of drafts, including their IDs and subjects. page_token can be used to paginate the results. To retrieve subsequent pages of results, use the page_token returned in the previous response.

The following sample demonstrate how to use curl to invoke the list_drafts MCP tool.

Curl Request 
curl --location 'https://gmailmcp.googleapis.com/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "method": "tools/call",
  "params": {
    "name": "list_drafts",
    "arguments": {
      // provide these details according to the tool's MCP specification
    }
  },
  "jsonrpc": "2.0",
  "id": 1
}'

Input Schema

Request message for ListDrafts RPC.

ListDraftsRequest

JSON representation 
{

  "pageSize": integer

  "pageToken": string

  "query": string
}
Fields

Union field _page_size.

_page_size can be only one of the following:
pageSize

integer

Optional. The maximum number of drafts to return. If unspecified, defaults to 20. The maximum allowed value is 50.

Union field _page_token.

_page_token can be only one of the following:
pageToken

string

Optional. A token received from a previous list_drafts call to retrieve the next page of results. Leave empty to fetch the first page. This is primarily used for pagination to continue fetching results from where the previous ListDraft call left off, especially when the number of drafts matching the query exceeds the page_size limit.

Union field _query.

_query can be only one of the following:
query

string

Examples: "subject:OneMCP Update" "from:gduser1@workspacesamples.dev" "to:gduser2@workspacesamples.dev AND newer_than:7d" "project proposal has:attachment" "is:unread"

A space or a dash (-) will separate a number while a dot (.) will be a decimal. For example, 01.2047-100 is considered two numbers: 01.2047 and 100.

Note: If we want to ensure all drafts for the query are returned, we can paginate the results by making repeated calls to the tool until the response contains an empty list of drafts.

Output Schema

Response message for ListDrafts RPC.

ListDraftsResponse

JSON representation 
{
  "drafts": [
    {
      object (Draft)
    }
  ],
  "nextPageToken": string
}
Fields
drafts[]

object (Draft)

List of drafts.
nextPageToken

string

A token that can be used in a subsequent call to retrieve the next page of drafts. If the number of drafts matching the query exceeds the page_size limit, the response will contain a next_page_token. To retrieve the next page of results, pass this token in the page_token field of the next ListDraftsRequest.

Draft

JSON representation 
{
  "id": string,
  "subject": string,
  "threadId": string,
  "toRecipients": [
    string
  ],
  "ccRecipients": [
    string
  ],
  "bccRecipients": [
    string
  ],
  "plaintextBody": string,
  "date": string
}
Fields
id

string

The unique identifier of the draft resource.
subject

string

The subject line of the draft message.
threadId

string

The ID of the thread this draft belongs to.
toRecipients[]

string

List of 'To' recipient email addresses extracted from headers.
ccRecipients[]

string

List of 'Cc' recipient email addresses extracted from headers.
bccRecipients[]

string

List of 'Bcc' recipient email addresses extracted from headers.
plaintextBody

string

Plain text body content, if available.
date

string

Date of the draft in ISO 8601 format (YYYY-MM-DD).

Tool Annotations

Destructive Hint: ❌ | Idempotent Hint: ❌ | Read Only Hint: ❌ | Open World Hint: ❌