Skip to main content
Glama
Davison-Francis

@deliveriq/mcp

Find Business Email

deliveriq_find_email
Idempotent

Find a person's business email address by providing their first and last name along with their company domain or company name. Validates email through pattern generation, SMTP probing, and public source corroboration.

Instructions

Find a person's business email address by name and company domain. Uses pattern generation, SMTP probing, corroboration from public sources, and org intelligence.

Args:

  • first_name (string): Person's first name

  • last_name (string): Person's last name

  • domain (string, optional): Company domain (e.g. "acme.com"). Required if company_name is not set

  • middle_name (string, optional): Middle name for disambiguation

  • company_name (string, optional): Company name, used to resolve domain if domain is not provided

Returns: Found email address, confidence score and label, verification method, and domain context.

Examples:

  • "Find John Doe at acme.com" -> { first_name: "John", last_name: "Doe", domain: "acme.com" }

  • "Find Jane Smith at Globex Corp" -> { first_name: "Jane", last_name: "Smith", company_name: "Globex Corp" }

Credit cost: 2 credits per lookup

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
first_nameYesFirst name of the person (e.g. "John")
last_nameYesLast name of the person (e.g. "Doe")
domainNoCompany domain (e.g. "acme.com"). Required if company_name is not provided
middle_nameNoMiddle name (improves accuracy for common names)
company_nameNoCompany name (e.g. "Acme Corp"). Used if domain is not provided

Implementation Reference

  • The registerIntelligenceTools function registers the 'deliveriq_find_email' tool with the MCP server. The handler (lines 45-95) calls client.emailFinder.find() with name and domain params, then formats a detailed response including email, confidence score, verification method, domain context, and corroboration signals.
    export function registerIntelligenceTools(server: McpServer, client: DeliverIQ): void {
      // ── 6. deliveriq_find_email ───────────────────────────────────
    
      server.registerTool(
        'deliveriq_find_email',
        {
          title: 'Find Business Email',
          description: `Find a person's business email address by name and company domain. Uses pattern generation, SMTP probing, corroboration from public sources, and org intelligence.
    
    Args:
      - first_name (string): Person's first name
      - last_name (string): Person's last name
      - domain (string, optional): Company domain (e.g. "acme.com"). Required if company_name is not set
      - middle_name (string, optional): Middle name for disambiguation
      - company_name (string, optional): Company name, used to resolve domain if domain is not provided
    
    Returns:
      Found email address, confidence score and label, verification method, and domain context.
    
    Examples:
      - "Find John Doe at acme.com" -> { first_name: "John", last_name: "Doe", domain: "acme.com" }
      - "Find Jane Smith at Globex Corp" -> { first_name: "Jane", last_name: "Smith", company_name: "Globex Corp" }
    
    Credit cost: 2 credits per lookup`,
          inputSchema: FindEmailSchema,
          annotations: {
            readOnlyHint: false,
            destructiveHint: false,
            idempotentHint: true,
            openWorldHint: true,
          },
        },
        async (params) => {
          try {
            const res = await client.emailFinder.find({
              firstName: params.first_name,
              lastName: params.last_name,
              domain: params.domain,
              middleName: params.middle_name,
              companyName: params.company_name,
            });
    
            const r = res.result;
            const lines = [
              `# Email Finder: ${res.firstName} ${res.lastName} @ ${res.domain}`,
              '',
            ];
    
            if (r.email) {
              lines.push(
                `**Email**: ${r.email}`,
                `**Confidence**: ${r.confidence}% (${r.confidenceLabel})`,
                `**Method**: ${r.verificationMethod.replace(/_/g, ' ')}`,
              );
              if (r.pattern) lines.push(`**Pattern**: ${r.pattern}`);
            } else {
              lines.push('**Result**: No email found.');
              if (r.probeDetails?.failureReason) {
                lines.push(`**Reason**: ${r.probeDetails.failureReason}`);
              }
            }
    
            lines.push(
              '',
              '## Domain Context',
              `- MX Provider: ${r.domainContext.mxProvider ?? 'Unknown'}`,
              `- Catch-all: ${r.domainContext.isCatchAll ? 'Yes' : 'No'}`,
              `- Infrastructure Score: ${r.domainContext.infrastructureScore ?? 'N/A'}`,
            );
    
            if (r.corroboration && r.corroboration.signals.length > 0) {
              lines.push('', '## Corroboration');
              for (const sig of r.corroboration.signals) {
                lines.push(`- ${sig.source}: ${sig.found ? 'Found' : 'Not found'}${sig.matchedEmail ? ` (${sig.matchedEmail})` : ''}`);
              }
            }
    
            lines.push('', `*Completed in ${r.durationMs}ms*`);
            return successResponse(lines.join('\n'));
          } catch (error) {
            return handleSdkError(error);
          }
        },
      );
  • Zod schema defining input validation for deliveriq_find_email: first_name (required string), last_name (required string), domain (optional string), middle_name (optional string), company_name (optional string). The schema is strict (no extra properties allowed).
    import { z } from 'zod';
    
    export const FindEmailSchema = z.object({
      first_name: z.string().min(1)
        .describe('First name of the person (e.g. "John")'),
      last_name: z.string().min(1)
        .describe('Last name of the person (e.g. "Doe")'),
      domain: z.string().optional()
        .describe('Company domain (e.g. "acme.com"). Required if company_name is not provided'),
      middle_name: z.string().optional()
        .describe('Middle name (improves accuracy for common names)'),
      company_name: z.string().optional()
        .describe('Company name (e.g. "Acme Corp"). Used if domain is not provided'),
    }).strict();
  • The tool is registered via server.registerTool('deliveriq_find_email', ...) with title 'Find Business Email', description with usage instructions, inputSchema set to FindEmailSchema, and annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint).
      server.registerTool(
        'deliveriq_find_email',
        {
          title: 'Find Business Email',
          description: `Find a person's business email address by name and company domain. Uses pattern generation, SMTP probing, corroboration from public sources, and org intelligence.
    
    Args:
      - first_name (string): Person's first name
      - last_name (string): Person's last name
      - domain (string, optional): Company domain (e.g. "acme.com"). Required if company_name is not set
      - middle_name (string, optional): Middle name for disambiguation
      - company_name (string, optional): Company name, used to resolve domain if domain is not provided
    
    Returns:
      Found email address, confidence score and label, verification method, and domain context.
    
    Examples:
      - "Find John Doe at acme.com" -> { first_name: "John", last_name: "Doe", domain: "acme.com" }
      - "Find Jane Smith at Globex Corp" -> { first_name: "Jane", last_name: "Smith", company_name: "Globex Corp" }
    
    Credit cost: 2 credits per lookup`,
          inputSchema: FindEmailSchema,
          annotations: {
            readOnlyHint: false,
            destructiveHint: false,
            idempotentHint: true,
            openWorldHint: true,
          },
        },
  • Constant CREDIT_COSTS defines the credit cost for deliveriq_find_email as 2 credits per lookup.
    export const CREDIT_COSTS: Record<string, number | string> = {
      deliveriq_verify_email: 1,
      deliveriq_batch_verify: '1 per email',
      deliveriq_batch_status: 0,
      deliveriq_batch_download: 0,
      deliveriq_list_jobs: 0,
      deliveriq_find_email: 2,
      deliveriq_blacklist_check: 1,
      deliveriq_infrastructure_check: 1,
      deliveriq_spam_trap_analysis: 1,
      deliveriq_domain_intel: 1,
      deliveriq_org_intel: 0,
      deliveriq_check_credits: 0,
    };
Behavior3/5

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

The description adds behavioral context beyond annotations, such as credit cost and the use of methods like pattern generation and SMTP probing. However, it does not fully disclose side effects or rate limits, and annotations indicate it is not read-only (readOnlyHint=false) which aligns with credit consumption. The description is adequate but could be more thorough.

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

Conciseness4/5

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

The description is well-structured with clear sections for arguments, returns, examples, and credit cost. It is concise but not overly terse. Each part serves a purpose, though some minor redundancy exists (e.g., repeating parameter details already in schema).

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

Completeness5/5

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

Given the tool's simplicity and the absence of an output schema, the description fully explains what the tool returns (email, confidence score, verification method, domain context) and covers credit cost. There are no apparent gaps in information needed to use the tool correctly.

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 description coverage is 100%, so parameters are already documented in the schema. The description adds value by explaining the mutual exclusivity of domain and company_name, and provides usage examples that clarify how to use the parameters. This goes beyond a baseline of 3.

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 tool's purpose: 'Find a person's business email address by name and company domain.' It uses a specific verb-resource combination and distinguishes from siblings like deliveriq_verify_email (which verifies an existing email) by focusing on discovery. The purpose is unambiguous.

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?

The description provides clear usage guidance through examples and by explaining the two ways to specify the target (domain or company_name). It implicitly distinguishes from the sibling verification tool, but does not explicitly state when not to use or provide alternative tools. This is good but not perfect.

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/Davison-Francis/min8t-sdks'

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