io.github.byteplant-dev/byteplant-mcp

This is an MCP server that connects AI assistants such as Claude, Cursor and VS Code to the Byteplant validation APIs. Ask your assistant to check an email address, phone number or postal address, and it calls the matching Byteplant tool and reads back the result.

The server runs locally on your computer and talks to your MCP client over stdio.

Installation

The easiest way to run the server is with uv. uvx downloads the package and a suitable Python version automatically, so there is nothing else to install.

Add the server to your MCP client with one of the configurations below, and replace the placeholders with your API keys. You only need the keys for the services you use.

Claude Desktop

1. In Claude Desktop, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json:

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

2. Add the Byteplant server:

   json

   {
     "mcpServers": {
       "byteplant": {
         "command": "uvx",
         "args": ["byteplant-mcp@latest"],
         "env": {
           "EV_TOKEN": "<EMAIL VALIDATOR API KEY>",
           "PV_TOKEN": "<PHONE VALIDATOR API KEY>",
           "AV_TOKEN": "<ADDRESS VALIDATOR API KEY>"
         }
       }
     }
   }
   

3. Restart Claude Desktop.

Claude Code

claude mcp add \
  --env EV_TOKEN=<EMAIL VALIDATOR API KEY> \
  --env PV_TOKEN=<PHONE VALIDATOR API KEY> \
  --env AV_TOKEN=<ADDRESS VALIDATOR API KEY> \
  --transport stdio byteplant -- uvx byteplant-mcp@latest

Cursor

Add the same mcpServers entry as for Claude Desktop to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project).

VS Code

Add the server to .vscode/mcp.json in your project:

{
  "servers": {
    "byteplant": {
      "type": "stdio",
      "command": "uvx",
      "args": ["byteplant-mcp@latest"],
      "env": {
        "EV_TOKEN": "<EMAIL VALIDATOR API KEY>",
        "PV_TOKEN": "<PHONE VALIDATOR API KEY>",
        "AV_TOKEN": "<ADDRESS VALIDATOR API KEY>"
      }
    }
  }
}

Using pip instead of uv

pip install byteplant-mcp

This installs a byteplant-mcp command. Use its full path as the command, because desktop apps often don't see your shell's PATH (find it with which byteplant-mcp on macOS/Linux or where byteplant-mcp on Windows):

"command": "/full/path/to/byteplant-mcp"

Alternatively, run the module with the Python installation you installed it into:

"command": "/path/to/python",
"args": ["-m", "byteplant_mcp"]

Tools

Credentials

Each tool uses its own API key, passed to the server as an environment variable. Sign up for the service you need to get one:

You can manage your keys in your Byteplant account. If a key is missing, the matching tool tells the assistant which variable to set instead of calling the API.

Usage

Just ask your assistant in plain language, for example:

• "Is support@byteplant.com a valid email address?"
• "Check whether +49 9874 322466 is a mobile or a landline number."
• "Validate this address and give me the standardized version: Heilsbronner Str. 4, 91564 Neuendettelsau, Germany."

The assistant fills in the tool parameters below. Every tool also has a timeout parameter, which sets how long the API may take to respond: 5–300 seconds, 10 by default.

validate_email - API Docs

Output

validate_phone - API Docs

Output

validate_address - API Docs

Output

Compatibility

ChatGPT and Claude on the web or mobile only connect to remote (hosted) MCP servers, so they can't use this server yet.

Resources

• Model Context Protocol documentation
• Email Validator API documentation
• Phone Validator API documentation
• Address Validator API documentation
• Byteplant website
• Contact: contact@byteplant.com

License

MIT