Skip to main content
Glama
lobster-kit

mcp-server-lobstermail

by lobster-kit

Create Email Inbox

create_inbox

Generate a new email inbox with a LobsterMail.ai address for AI agents. Provide a name or organization to create a meaningful address, or get a random one automatically.

Instructions

Create a new email inbox. Returns an @lobstermail.ai address. Provide your name/org for a meaningful address (e.g. sarah-shield@lobstermail.ai), or omit for a random lobster-xxxx address.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoYour name or agent name (e.g. "Sarah Shield")
orgNoOrganization name (e.g. "Palisade")
preferredNoExplicit local parts to try first (e.g. ["billing-bot", "billing"])
displayNameNoDisplay name for the inbox

Implementation Reference

  • The `create_inbox` tool registration and handler logic. It uses the `lm` client to either create a smart inbox or a standard inbox, then caches it and returns the details.
    server.registerTool('create_inbox', {
      title: 'Create Email Inbox',
      description:
        'Create a new email inbox. Returns an @lobstermail.ai address. ' +
        'Provide your name/org for a meaningful address (e.g. sarah-shield@lobstermail.ai), ' +
        'or omit for a random lobster-xxxx address.',
      inputSchema: {
        name: z.string().optional().describe('Your name or agent name (e.g. "Sarah Shield")'),
        org: z.string().optional().describe('Organization name (e.g. "Palisade")'),
        preferred: z
          .array(z.string())
          .optional()
          .describe('Explicit local parts to try first (e.g. ["billing-bot", "billing"])'),
        displayName: z.string().optional().describe('Display name for the inbox'),
      },
    }, async ({ name, org, preferred, displayName }) => {
      const lm = await getClient();
      const hasSmartOpts = name || org || preferred;
      const inbox = hasSmartOpts
        ? await lm.createSmartInbox({ name, org, preferred, displayName })
        : await lm.createInbox({ displayName });
      cacheInbox(inbox);
    
      return {
        content: [
          {
            type: 'text' as const,
            text: [
              `Inbox created successfully.`,
              ``,
              `Address: ${inbox.address}`,
              `Inbox ID: ${inbox.id}`,
              `Active: ${inbox.isActive}`,
              inbox.expiresAt ? `Expires: ${inbox.expiresAt}` : null,
              ``,
              `Use this inbox_id with check_inbox, wait_for_email, and other tools.`,
            ]
              .filter(Boolean)
              .join('\n'),
          },
        ],
      };
    });
Behavior3/5

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

No annotations provided, so description carries full burden. Adds critical behavioral context: returns specific domain (@lobstermail.ai) and explains address generation logic (meaningful hyphenated name vs random lobster-xxxx). Missing: conflict resolution (if name taken), idempotency, rate limits, or persistence guarantees.

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?

Two sentences, zero waste. First sentence establishes purpose and return value. Second sentence covers parameter usage patterns and examples. Front-loaded with essential 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?

No output schema exists, yet description adequately specifies return format (lobstermail.ai address). Explains parameter interaction logic (name+org vs omit). Missing explicit error handling (e.g., 'what if preferred name is taken'), but adequate for a 4-parameter optional tool.

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?

Schema coverage is 100% (all 4 params documented). Description adds semantic value beyond schema by explaining how 'name' and 'org' combine to create a 'meaningful address' with example transformation (Sarah Shield → sarah-shield), and the alternative 'random' path. Schema handles preferred/displayName sufficiently.

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?

States specific verb 'Create' and resource 'email inbox'. Explicitly distinguishes from siblings (check_inbox, delete_inbox, list_inboxes) by being the sole creation entry point. Mentions return value (@lobstermail.ai) clarifying output scope.

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 conditional logic: 'Provide your name/org... or omit for a random lobster-xxxx address.' This guides when to populate optional parameters versus leaving them empty. Does not explicitly name sibling alternatives, but clearly delineates the creation use-case.

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