AI Agent Protocol

Model Context Protocol (MCP) Server Setup

Native Model Context Protocol (MCP) server allowing AI coding assistants (Cursor, Claude Desktop, Windsurf, Claude Code CLI) to verify emails autonomously via natural language prompts.

Quick Install (1 Command)

bash
npx -y @bouncelayer/mcp

1. Cursor IDE Setup

Add to .cursor/mcp.json in your project root or ~/.cursor/mcp.json globally:

json
{
  "mcpServers": {
    "bouncelayer": {
      "command": "npx",
      "args": ["-y", "@bouncelayer/mcp"],
      "env": {
        "BOUNCELAYER_API_KEY": "bl_live_your_api_key_here"
      }
    }
  }
}

2. Claude Desktop Setup

Add to claude_desktop_config.json on macOS (~/Library/Application Support/Claude/claude_desktop_config.json) or Windows (%APPDATA%\Claude\claude_desktop_config.json):

json
{
  "mcpServers": {
    "bouncelayer": {
      "command": "npx",
      "args": ["-y", "@bouncelayer/mcp"],
      "env": {
        "BOUNCELAYER_API_KEY": "bl_live_your_api_key_here"
      }
    }
  }
}

3. Claude Code CLI Setup

bash
claude mcp add --transport http bouncelayer https://api.bouncelayer.com/mcp/ --header "X-API-Key: bl_live_your_api_key_here"

Autonomous Agent Usage Examples

Once connected, your AI assistant can execute verification autonomously:

  • "Verify alex@stripe.com and inspect if their mail server supports TLS."
  • "Clean this CSV of 500 leads and save only the valid 250 OK contacts to clean_leads.csv."
  • "Check my remaining BounceLayer verification credits."