MCP 服务器

trykittai-mcp-server

README

TryKitt.ai mcp Server

A FastMCP (Model Context Protocol) server that provides email verification and finding capabilities using the TryKitt.ai API. This server enables AI assistants to find and verify B2B email addresses with high accuracy and low bounce rates.

Features

Email Verification: Verify email addresses with advanced SMTP and catchall verification
Email Finding: Find email addresses for individuals using their name and company domain
Job Management: Track and monitor email verification/finding jobs
Real-time Processing: Get immediate results for email operations
High Accuracy: Leverages TryKitt.ai's advanced verification algorithms with <0.1% bounce rate

Installation

Clone this repository:

git clone https://github.com/avivshafir/trykittai-mcp-server
cd trykittai-mcp-server

Initialize a new Python environment with uv:

# Initialize a new uv project (if starting fresh)
uv init

# Or create a virtual environment
uv venv

# Activate the virtual environment
source .venv/bin/activate  # On macOS/Linux

Install dependencies using uv:

# Using uv (recommended)
uv sync

Setup

Get your TryKitt.ai API key:
- Visit TryKitt.ai
- Sign up for an account
- Navigate to your API settings to get your API key
Set your API key as an environment variable:

export TRYKITT_API_KEY="your_api_key_here"

Or create a .env file in the project root:

TRYKITT_API_KEY=your_api_key_here

Usage

Running the Server

Start the FastMCP server:

python server.py

The server will start and be available for MCP connections.

Adding to MCP Clients

To use this server with MCP-compatible clients, you'll need to configure the client to connect to this server.

Claude Desktop

Add the following configuration to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "trykittai": {
      "command": "python",
      "args": ["/path/to/your/trykittai-mcp-server/server.py"],
      "env": {
        "TRYKITT_API_KEY": "your_api_key_here"
      }
    }
  }
}

Other MCP Clients

For other MCP-compatible clients, configure them to connect to:

Command: python
Arguments: ["/path/to/your/trykittai-mcp-server/server.py"]
Environment Variables: TRYKITT_API_KEY=your_api_key_here

Using with uv

If you're using uv, you can also run the server with:

{
  "mcpServers": {
    "trykittai": {
      "command": "uv",
      "args": ["run", "python", "server.py"],
      "cwd": "/path/to/your/trykittai-mcp-server",
      "env": {
        "TRYKITT_API_KEY": "your_api_key_here"
      }
    }
  }
}

Note: Replace /path/to/your/trykittai-mcp-server with the actual absolute path to your project directory, and your_api_key_here with your actual TryKitt.ai API key.

Available Tools

1. Email Verification (`verify_email_send`)

Verify if an email address is valid and deliverable.

Parameters:

email (required): The email address to verify
custom_data (optional): Custom data to associate with the request

Example:

result = await verify_email_send("john.doe@example.com")

2. Email Finding (`find_email`)

Find an email address for a person based on their name and company domain.

Parameters:

full_name (required): The full name of the person
domain (required): The company domain or website
linkedin_url (optional): LinkedIn profile URL for better accuracy
custom_data (optional): Custom data to associate with the request

Example:

result = await find_email(
    full_name="John Doe",
    domain="example.com",
    linkedin_url="https://linkedin.com/in/johndoe"
)

3. Job Status (`get_job_status`)

Check the status of a previously submitted job.

Parameters:

job_id (required): The ID of the job to check

Example:

result = await get_job_status("job_123456")

4. List Jobs (`list_jobs`)

List all jobs (Note: This endpoint may have limited availability).

Example:

result = await list_jobs()

API Response Format

Successful Email Verification

{
  "id": "job_123456",
  "status": "completed",
  "result": {
    "email": "john.doe@example.com",
    "valid": true,
    "deliverable": true,
    "confidence": 0.95,
    "verification_type": "smtp_catchall"
  }
}

Successful Email Finding

{
  "id": "job_789012",
  "status": "completed",
  "result": {
    "email": "john.doe@example.com",
    "confidence": 0.88,
    "sources": ["pattern_matching", "web_scraping"]
  }
}

Error Handling

The server handles various error scenarios:

Invalid API keys
Rate limiting
Network timeouts
Invalid email formats
Domain verification failures

Common error responses:

{
  "error": "Invalid API key",
  "code": 401
}

Configuration

Environment Variables

TRYKITT_API_KEY: Your TryKitt.ai API key (required)

SSL Configuration

The server is configured to work with TryKitt.ai's API endpoints. SSL verification is currently disabled for compatibility.

Development

Project Structure

trykittai-mcp-server/
├── server.py          # Main FastMCP server implementation
├── pyproject.toml     # Project dependencies and configuration
├── uv.lock           # Dependency lock file
├── README.md         # This file
├── LICENSE           # MIT License
└── .venv/            # Virtual environment