Skip to main content
Glama

get_draft

Retrieve a specific email draft from Gmail by its ID, with options to include or exclude HTML content for efficient data handling.

Instructions

Get a specific draft by ID

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesThe ID of the draft to retrieve
includeBodyHtmlNoWhether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large

Implementation Reference

  • Handler function for the 'get_draft' tool. Fetches the specified draft using the Gmail API, processes its message payload (decoding body and filtering headers), and returns a formatted JSON response.
    async (params) => { return handleTool(config, async (gmail: gmail_v1.Gmail) => { const { data } = await gmail.users.drafts.get({ userId: 'me', id: params.id, format: 'full' }) if (data.message?.payload) { data.message.payload = processMessagePart( data.message.payload, params.includeBodyHtml ) } return formatResponse(data) }) }
  • Zod input schema for the 'get_draft' tool defining parameters: id (required string) and includeBodyHtml (optional boolean).
    { id: z.string().describe("The ID of the draft to retrieve"), includeBodyHtml: z.boolean().optional().describe("Whether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large") },
  • src/index.ts:297-317 (registration)
    Registration of the 'get_draft' tool on the MCP server using server.tool(), including description, input schema, and inline handler function.
    server.tool("get_draft", "Get a specific draft by ID", { id: z.string().describe("The ID of the draft to retrieve"), includeBodyHtml: z.boolean().optional().describe("Whether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large") }, async (params) => { return handleTool(config, async (gmail: gmail_v1.Gmail) => { const { data } = await gmail.users.drafts.get({ userId: 'me', id: params.id, format: 'full' }) if (data.message?.payload) { data.message.payload = processMessagePart( data.message.payload, params.includeBodyHtml ) } return formatResponse(data) }) } )
  • Shared helper function used by 'get_draft' (and other tools) to handle OAuth2 authentication, client creation, credential validation, and API call execution.
    const handleTool = async (queryConfig: Record<string, any> | undefined, apiCall: (gmail: gmail_v1.Gmail) => Promise<any>) => { try { const oauth2Client = queryConfig ? createOAuth2Client(queryConfig) : defaultOAuth2Client if (!oauth2Client) throw new Error('OAuth2 client could not be created, please check your credentials') const credentialsAreValid = await validateCredentials(oauth2Client) if (!credentialsAreValid) throw new Error('OAuth2 credentials are invalid, please re-authenticate') const gmailClient = queryConfig ? google.gmail({ version: 'v1', auth: oauth2Client }) : defaultGmailClient if (!gmailClient) throw new Error('Gmail client could not be created, please check your credentials') const result = await apiCall(gmailClient) return result } catch (error: any) { return `Tool execution failed: ${error.message}` } }
  • Recursive helper function to process message parts: decodes base64 bodies (except HTML unless specified), processes nested parts, and filters headers to include only specified ones.
    const processMessagePart = (messagePart: MessagePart, includeBodyHtml = false): MessagePart => { if ((messagePart.mimeType !== 'text/html' || includeBodyHtml) && messagePart.body) { messagePart.body = decodedBody(messagePart.body) } if (messagePart.parts) { messagePart.parts = messagePart.parts.map(part => processMessagePart(part, includeBodyHtml)) } if (messagePart.headers) { messagePart.headers = messagePart.headers.filter(header => RESPONSE_HEADERS_LIST.includes(header.name || '')) } return messagePart }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nk900600/gmail-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server