Skip to main content
Glama
lobster-kit

mcp-server-lobstermail

by lobster-kit

Send Email

send_email

Send emails from verified LobsterMail inboxes. Compose messages with text or HTML, add recipients and CCs, and reply within threads using Message-ID.

Instructions

Send an email from an inbox. Requires a verified account (Tier 1+). To reply within a thread, provide in_reply_to with the Message-ID of the email being replied to.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inbox_idYesInbox ID to send from
toYesRecipient email addresses
subjectYesEmail subject
body_textYesPlain text email body
body_htmlNoHTML email body (optional)
ccNoCC recipients
in_reply_toNoMessage-ID of the email being replied to (enables threading)

Implementation Reference

  • The tool registration and handler implementation for 'send_email' in src/index.ts. It defines the input schema for email sending and uses an inbox object to dispatch the email.
    server.registerTool('send_email', {
      title: 'Send Email',
      description:
        'Send an email from an inbox. Requires a verified account (Tier 1+). ' +
        'To reply within a thread, provide in_reply_to with the Message-ID of the email being replied to.',
      inputSchema: {
        inbox_id: z.string().describe('Inbox ID to send from'),
        to: z.array(z.string()).describe('Recipient email addresses'),
        subject: z.string().describe('Email subject'),
        body_text: z.string().describe('Plain text email body'),
        body_html: z.string().optional().describe('HTML email body (optional)'),
        cc: z.array(z.string()).optional().describe('CC recipients'),
        in_reply_to: z.string().optional().describe('Message-ID of the email being replied to (enables threading)'),
      },
    }, async ({ inbox_id, to, subject, body_text, body_html, cc, in_reply_to }) => {
      const inbox = await getInbox(inbox_id);
      const result = await inbox.send({
        to,
        cc,
        subject,
        body: { text: body_text, html: body_html },
        inReplyTo: in_reply_to,
      });
    
      return {
        content: [
          {
            type: 'text' as const,
            text: `Email queued for delivery.\n\nEmail ID: ${result.id}\nStatus: ${result.status}`,
          },
        ],
      };
    });
Behavior3/5

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

With no annotations provided, the description carries the full burden. It successfully discloses the authentication requirement (Tier 1+) and threading mechanics, but omits other behavioral traits like error handling, delivery guarantees, or idempotency that would be expected for a mutation operation.

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 well-structured sentences: the first establishes purpose, the second states prerequisites, and the third provides specific parameter guidance. No redundancy or wasted words; front-loaded with critical information.

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 7-parameter mutation tool with 100% schema coverage, the description adequately covers the critical operational constraints (auth tier, threading). The lack of output schema prevents a 5, as the description doesn't clarify what the tool returns upon success.

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?

While the schema has 100% coverage providing baseline documentation for all 7 parameters, the description adds valuable semantic context specifically for 'in_reply_to' by explaining it requires a Message-ID and enables threading behavior, exceeding the schema's basic description.

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?

The description clearly states the specific action ('Send an email'), the resource (email), and the source ('from an inbox'), making it immediately distinguishable from sibling tools like check_inbox, get_email, or create_inbox.

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

Usage Guidelines4/5

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

Provides explicit prerequisites ('Requires a verified account (Tier 1+)') and specific usage context for threading ('To reply within a thread...'). However, it does not explicitly name sibling alternatives or when-not-to-use scenarios.

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

Install Server

Other Tools

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/lobster-kit/mcp-server-lobstermail'

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