Skip to main content
Glama
ricleedo

Google Services MCP Server

by ricleedo

gmail-get-email

Retrieve a specific Gmail email using its message ID to access individual messages within the Google Services MCP Server.

Instructions

Get a specific email by message ID

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageIdYesGmail message ID

Implementation Reference

  • The handler function that retrieves a specific Gmail email by message ID using the Google Gmail API, extracts headers and body (handling multipart), truncates long body, formats as Markdown using formatEmailToMarkdown, and returns structured content.
    export async function getEmail(params: z.infer<typeof getEmailSchema>) {
      try {
        const auth = createGmailAuth();
        const gmail = google.gmail({ version: "v1", auth });
    
        const response = await gmail.users.messages.get({
          userId: "me",
          id: params.messageId,
          format: "full",
        });
    
        const message = response.data;
        const headers = message.payload?.headers || [];
        const getHeader = (name: string) =>
          headers.find((h) => h.name?.toLowerCase() === name.toLowerCase())
            ?.value || "";
    
        // Extract body content
        let body = "";
        if (message.payload?.body?.data) {
          body = Buffer.from(message.payload.body.data, "base64").toString();
        } else if (message.payload?.parts) {
          // Handle multipart messages
          for (const part of message.payload.parts) {
            if (part.mimeType === "text/plain" && part.body?.data) {
              body = Buffer.from(part.body.data, "base64").toString();
              break;
            }
          }
        }
    
        // Truncate body if it exceeds 30000 characters
        const truncatedBody =
          body.length > 20000
            ? body.substring(0, 20000) +
              "\n\n[Email body truncated - content too long]"
            : body;
    
        const emailDetail = {
          id: message.id,
          threadId: message.threadId,
          from: getHeader("From"),
          to: getHeader("To"),
          cc: getHeader("Cc"),
          bcc: getHeader("Bcc"),
          subject: getHeader("Subject"),
          date: getHeader("Date"),
          body: truncatedBody,
          snippet: message.snippet,
          labelIds: message.labelIds,
        };
    
        return {
          content: [
            {
              type: "text" as const,
              text: formatEmailToMarkdown(emailDetail),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error getting email: ${
                error instanceof Error ? error.message : String(error)
              }`,
            },
          ],
        };
      }
    }
  • Zod schema for input validation: requires 'messageId' as a string.
    export const getEmailSchema = z.object({
      messageId: z.string().describe("Gmail message ID"),
    });
  • src/index.ts:200-207 (registration)
    MCP server registration of the 'gmail-get-email' tool, using getEmailSchema and delegating to the getEmail handler.
    server.tool(
      "gmail-get-email",
      "Get a specific email by message ID",
      getEmailSchema.shape,
      async (params) => {
        return await getEmail(params);
      }
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Get') but doesn't describe what 'get' returns (e.g., full email content, headers, attachments), error conditions (e.g., invalid ID, permissions), or side effects (e.g., marking as read). For a read operation with zero annotation coverage, this leaves significant gaps in understanding the tool's behavior.

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?

The description is a single, direct sentence with zero wasted words. It front-loads the core action ('Get a specific email') and specifies the key identifier ('by message ID'), making it highly efficient. Every part of the sentence contributes essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 parameter, no output schema, no annotations), the description is incomplete. It doesn't explain what 'get' returns (e.g., email body, metadata), potential errors, or how the message ID should be obtained. For a tool that retrieves data, this lack of output and behavioral context makes it inadequate for reliable agent use.

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?

The description doesn't add any parameter-specific information beyond what's in the input schema, which has 100% coverage (the 'messageId' parameter is fully described as 'Gmail message ID'). With high schema coverage, the baseline is 3, as the schema already documents the parameter adequately, and the description doesn't compensate with additional context like format examples or sourcing details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('a specific email'), making the purpose immediately understandable. It distinguishes from sibling tools like 'gmail-read-emails' (which lists emails) and 'gmail-send-email' (which sends emails). However, it doesn't specify what 'get' entails (e.g., retrieving full content vs metadata), which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a valid message ID), contrast with 'gmail-read-emails' for listing emails, or specify use cases like retrieving a single known email. Without such context, the agent must infer usage from the tool name alone.

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