Skip to main content
Glama
DynamicEndpoints

pocketbase-mcp-server

send_custom_email

Send personalized emails programmatically through PocketBase integration. This tool facilitates communication by customizing and delivering emails directly from the MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler function that sends custom email using nodemailer transporter and logs to PocketBase email_logs collection.
    async sendCustomEmail(data: {
      to: string;
      from?: string;
      subject: string;
      html: string;
      text?: string;
    }): Promise<EmailLog> {
      try {
        // Send email
        const info = await this.transporter.sendMail({
          from: data.from || process.env.SMTP_USER || process.env.DEFAULT_FROM_EMAIL,
          to: data.to,
          subject: data.subject,
          html: data.html,
          text: data.text,
        });      // Log email
        const emailLog = await this.pb.collection('email_logs').create({
          to: data.to,
          from: data.from || process.env.SMTP_USER || process.env.DEFAULT_FROM_EMAIL,
          subject: data.subject,
          status: 'sent',
        });
    
        return emailLog as unknown as EmailLog;
      } catch (error: any) {
        // Log failed email
        const emailLog = await this.pb.collection('email_logs').create({
          to: data.to,
          from: data.from || process.env.SMTP_USER || process.env.DEFAULT_FROM_EMAIL,
          subject: data.subject,
          status: 'failed',
          error: error.message,
        });
    
        throw new Error(`Failed to send custom email: ${error.message}`);
      }
    }
  • MCP server tool registration for 'send_custom_email' including input schema validation with zod and wrapper handler that invokes EmailService.sendCustomEmail
    this.server.tool(
      'send_custom_email',
      {
        description: 'Send a custom email with specified content',
        inputSchema: {
          to: z.string().email().describe('Recipient email address'),
          from: z.string().email().optional().describe('Sender email address'),
          subject: z.string().describe('Email subject'),
          html: z.string().describe('HTML email body'),
          text: z.string().optional().describe('Plain text email body')
        }
      },
      async ({ to, from, subject, html, text }) => {
        // Lazy load Email service
        await this.ensureEmailService();
        
        if (!this.emailService) {
          throw new Error('Email service not available. Please configure EMAIL_SERVICE or SMTP settings.');
        }
    
        try {
          const result = await this.emailService.sendCustomEmail({
            to,
            from,
            subject,
            html,
            text
          });
          return {
            content: [{
              type: 'text',
              text: JSON.stringify({
                success: true,
                emailLog: {
                  id: result.id,
                  to: result.to,
                  subject: result.subject,
                  status: result.status,
                  sentAt: result.created
                }
              }, null, 2)
            }]
          };
        } catch (error: any) {
          throw new Error(`Failed to send email: ${error.message}`);
        }
      }
    );
  • TypeScript type definition/schema for the sendCustomEmail method parameters.
    sendCustomEmail(data: {
        to: string;
        from?: string;
        subject: string;
        html: string;
        text?: string;
    }): Promise<EmailLog>;
  • Another MCP tool registration for 'send_custom_email' in the best-practices agent with similar schema and handler.
      {
        to: EmailAddressSchema,
        from: EmailAddressSchema.optional(),
        subject: z.string().describe('Email subject'),
        htmlBody: z.string().optional().describe('HTML email body'),
        textBody: z.string().optional().describe('Plain text email body')
      },
      async ({ to, from, subject, htmlBody, textBody }) => {
        try {
          if (!this.emailService) {
            return this.createErrorResponse('Email service not available');
          }
    
          const result = await this.emailService.sendCustomEmail({
            to,
            from,
            subject,
            html: htmlBody || '',
            text: textBody
          });
          
          return {
            content: [{
              type: 'text',
              text: JSON.stringify({
                success: true,
                emailLog: {
                  id: result.id,
                  to: result.to,
                  subject: result.subject,
                  status: result.status,
                  sentAt: result.created
                }
              }, null, 2)
            }]
          };
        } catch (error) {
          return this.createErrorResponse(error);
        }
      }
    );
  • JSON schema for send_custom_email tool in worker tools list for discovery.
    {
      name: 'send_custom_email',
      description: 'Send a custom email with specified content',
      inputSchema: {
        type: 'object',
        properties: {
          to: { type: 'string', format: 'email', description: 'Recipient email address' },
          from: { type: 'string', format: 'email', description: 'Sender email address' },
          subject: { type: 'string', description: 'Email subject' },
          html: { type: 'string', description: 'HTML email body' },
          text: { type: 'string', description: 'Plain text email body' }
        },
        required: ['to', 'subject', 'html']
      }
    }
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Related 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/DynamicEndpoints/pocketbase-mcp-server'

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