Skip to main content
Glama
railsware

Mailtrap Email Sending

by railsware

send-sandbox-email

Send test emails to a sandbox inbox to verify email content and formatting before delivering to actual recipients.

Instructions

Send an email in sandbox mode to a test inbox without delivering to your recipients

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fromYesEmail address of the sender
toYesEmail addresses (comma-separated or single)
subjectYesEmail subject line
ccNoOptional CC recipients
bccNoOptional BCC recipients
categoryNoOptional email category for tracking
textNoEmail body text
htmlNoOptional HTML version of the email body

Implementation Reference

  • The main handler function for the 'send-sandbox-email' tool. It constructs and sends an email using the Mailtrap sandbox client, handles validation, parsing of recipients, and returns success or error content.
    async function sendSandboxEmail({
      from,
      to,
      subject,
      text,
      cc,
      bcc,
      category,
      html,
    }: SendSandboxEmailRequest): Promise<{ content: any[]; isError?: boolean }> {
      try {
        const { MAILTRAP_TEST_INBOX_ID } = process.env;
    
        if (!MAILTRAP_TEST_INBOX_ID) {
          throw new Error(
            "MAILTRAP_TEST_INBOX_ID environment variable is required for sandbox mode"
          );
        }
    
        if (!html && !text) {
          throw new Error("Either HTML or TEXT body is required");
        }
    
        // Use provided 'from' email or fall back to DEFAULT_FROM_EMAIL
        const fromEmail = from || DEFAULT_FROM_EMAIL;
    
        if (!fromEmail) {
          throw new Error(
            "No 'from' email provided and no 'DEFAULT_FROM_EMAIL' email set"
          );
        }
    
        // Check if sandbox client is available
        if (!sandboxClient) {
          throw new Error(
            "Sandbox client is not available. Please set MAILTRAP_TEST_INBOX_ID environment variable."
          );
        }
    
        const fromAddress: Address = {
          email: fromEmail,
        };
    
        // Parse and validate email addresses from the 'to' string
        const toEmails = to
          .split(",")
          .map((email) => email.trim())
          .filter((email) => email.length > 0)
          .filter((email) => /^[^\s@]+@[^\s@]+\.[^\s@]+$/.test(email));
    
        if (toEmails.length === 0) {
          throw new Error("No valid email addresses provided in 'to' field");
        }
    
        const toAddresses: Address[] = toEmails.map((email) => ({ email }));
    
        const emailData: Mail = {
          from: fromAddress,
          to: toAddresses,
          subject,
          text,
          html,
          category,
        };
    
        if (cc && cc.length > 0) emailData.cc = cc.map((email) => ({ email }));
        if (bcc && bcc.length > 0) emailData.bcc = bcc.map((email) => ({ email }));
    
        const response = await sandboxClient.send(emailData);
    
        return {
          content: [
            {
              type: "text",
              text: `Sandbox email sent successfully to ${toEmails.join(
                ", "
              )}.\nMessage IDs: ${response.message_ids.join(", ")}\nStatus: ${
                response.success ? "Success" : "Failed"
              }`,
            },
          ],
        };
      } catch (error) {
        console.error("Error sending sandbox email:", error);
    
        const errorMessage = error instanceof Error ? error.message : String(error);
    
        return {
          content: [
            {
              type: "text",
              text: `Failed to send sandbox email: ${errorMessage}`,
            },
          ],
          isError: true,
        };
      }
    }
  • The input schema defining the parameters for the 'send-sandbox-email' tool, including from, to, subject, cc, bcc, category, text, html with required fields.
    const sendSandboxEmailSchema = {
      type: "object",
      properties: {
        from: {
          type: "string",
          format: "email",
          description: "Email address of the sender",
        },
        to: {
          type: "string",
          minLength: 1,
          description: "Email addresses (comma-separated or single)",
        },
        subject: {
          type: "string",
          description: "Email subject line",
        },
        cc: {
          type: "array",
          items: {
            type: "string",
            format: "email",
          },
          description: "Optional CC recipients",
        },
        bcc: {
          type: "array",
          items: {
            type: "string",
            format: "email",
          },
          description: "Optional BCC recipients",
        },
        category: {
          type: "string",
          description: "Optional email category for tracking",
        },
        text: {
          type: "string",
          description: "Email body text",
        },
        html: {
          type: "string",
          description: "Optional HTML version of the email body",
        },
      },
      required: ["from", "to", "subject"],
      additionalProperties: false,
    };
    
    export default sendSandboxEmailSchema;
  • src/server.ts:82-91 (registration)
    The registration of the 'send-sandbox-email' tool in the tools array, linking the name, description, schema, and handler.
    {
      name: "send-sandbox-email",
      description:
        "Send an email in sandbox mode to a test inbox without delivering to your recipients",
      inputSchema: sendSandboxEmailSchema,
      handler: sendSandboxEmail,
      annotations: {
        destructiveHint: false,
      },
    },
Behavior4/5

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

The description adds valuable behavioral context beyond the annotations. While annotations only indicate destructiveHint=false (non-destructive), the description clarifies that emails go to a 'test inbox' and won't reach actual recipients, which is crucial for understanding the tool's testing/simulation behavior. No contradiction with annotations exists.

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, efficient sentence that front-loads the key information (sandbox mode, test inbox, no delivery) with zero wasted words. Every element serves a clear purpose in distinguishing this tool's behavior.

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 tool with good annotations (destructiveHint=false) and full schema coverage, the description provides sufficient context about the sandbox/testing behavior. The main gap is the lack of output schema, but the description compensates by clarifying the test inbox destination. It adequately covers the tool's purpose and usage context.

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?

With 100% schema description coverage, all parameters are well-documented in the schema itself. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline of 3 for adequate coverage without extra value.

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') and resource ('in sandbox mode to a test inbox'), with explicit differentiation from normal email sending ('without delivering to your recipients'). It distinguishes from the sibling 'send-email' tool by specifying the sandbox/testing context.

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

Usage Guidelines5/5

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

The description explicitly states when to use this tool ('in sandbox mode to a test inbox') and when not to use it ('without delivering to your recipients'), providing clear context for testing versus production email sending. It implicitly contrasts with the sibling 'send-email' tool for actual delivery.

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/railsware/mailtrap-mcp'

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