Pulsiv MCP for AI Agents

MCP (Model Context Protocol) is a standard way for AI assistants to call external tools safely. Instead of hardcoding custom integrations for each assistant, you expose tools once through an MCP server.

Pulsiv's MCP server gives assistants direct access to your organization's alert workflows so they can create and manage on-chain monitoring tasks for you.

Once connected, your agent understands on-chain intent in plain English. Here are some prompts you can try:

• “Monitor USDC transfers on Ethereum where the value exceeds $200M and notify me on Telegram”

  ERC-20EthereumWhale alert

• “Alert me whenever a new governance proposal is submitted on Compound Finance”

  GovernanceDeFiCompound

• “Track all NFT mints from the Bored Ape Yacht Club contract and send me a Telegram message”

  NFTMintTelegram

• “List all my alerts”

  ManagementAlerts

• “Pause all my active alerts for USDT, then list what's still running”

  ManagementUSDTMulti-step

• “Delete all my paused alerts”

  ManagementAlerts

1. Sign in to Pulsiv and open Settings - API keys.
2. Create a new key and copy the full secret immediately (it is shown once).
3. Use that secret as a Bearer token in your MCP client configuration.

Add Pulsiv to your project or global Cursor MCP config:

{
  "mcpServers": {
    "pulsiv-mcp": {
      "url": "https://mcp.pulsiv.app",
      "headers": {
        "Authorization": "Bearer pulse_your_org_api_key"
      }
    }
  }
}

Run this command in your terminal to register Pulsiv as an MCP server in Claude:

$ claude mcp add --transport http pulsiv-mcp https://mcp.pulsiv.app \
  --header "Authorization: Bearer pulse_your_org_api_key"