Agent Quickstart

This guide gets an AI agent talking to XentFi through MCP — from creating an agent to seeing wallet data inside a chat client.

Prerequisites

A XentFi account (Sign up)
Node.js 18+ available wherever your MCP client spawns tools (most desktop clients bundle their own)
One of the supported clients: Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT, ElizaOS, CrewAI, or OpenAI Codex/Agents SDK

Step 1: Create an Agent and get its API key

Log into Dashboard

Navigate to dashboard.xentfi.com.

Create an Agent

Go to Agents → New Agent. This is the identity your AI will act as — separate from your own dashboard login.

Attach a Policy

Under Policies, create or attach a spend policy to the agent: per-transaction / daily / weekly / monthly USD limits, an allowed-recipients list, and (optionally) allowed hours. This is what keeps an autonomous agent from overspending or paying the wrong address — XentFi enforces it server-side on every payment.

Generate the API key

From the agent’s page, generate an new Agent. Copy the Agent key — it’s shown once.

An agent API key authorizes payments on behalf of that agent. Store it the same way you’d store any other production secret — never in source control or a chat log.

Step 2: Set your environment variables

export XENTFI_AGENT_KEY="sk_agent_xxx"

Step 3: Connect an MCP client

The fastest path is Claude Desktop. Add this to your MCP config (see Claude Desktop guide for the exact file path):

{
    "mcpServers": {
        "xentfi": {
            "command": "npx",
            "args": [
                "-y",
                "@xentfi/mcp-server"
            ],
            "env": {
                "XENTFI_AGENT_KEY": "sk_agent_xxx",
                "XENTFI_ORG_ID": "org_xxx"
            }
        }
    }
}

Restart the client, open a new chat, and confirm the xentfi server appears with 15 tools available.

Step 4: Make your first agent tool call

Ask your agent:

“Check my XentFi agent info and list my wallets.”

Behind the scenes this calls xentfi_get_agent_info then xentfi_list_wallets:

{
  "id": "agent_123e4567-e89b-12d3-a456-426614174000",
  "organizationId": "org_123e4567",
  "name": "Trading Agent",
  "status": "ACTIVE"
}

{
  "data": [
    {
      "id": "aw_123e4567-e89b-12d3-a456-426614174000",
      "agentId": "agent_123e4567",
      "isActive": true,
      "addressWallet": {
        "walletAddress": "0x742d35Cc6634C0532925a3b844Bc9e7595f0bEb0",
        "network": "base-mainnet"
      }
    }
  ],
  "total": 1,
  "hasMore": false
}

If data is empty, have the agent call xentfi_create_wallet first (see Tools Reference).

Step 5: Try a policy-checked payment

“Send 1 USDC to 0x… from my wallet.”

This calls xentfi_create_payment, which requires an explicit confirm: true and is evaluated against the agent’s Policy server-side:

{
    "agentWalletId": "aw_123e4567",
    "assetId": "asset_usdc_id",
    "recipient": "0x...",
    "amount": "1.00",
    "confirm": true
}

If it exceeds a limit or isn’t on the allowlist, you’ll get back a structured POLICY_DENIED result instead of a silent failure — see Error Handling.

Next steps

Tools Reference

Every tool, its arguments, and what it returns.

Choose your client

Guides for Claude, Cursor, VS Code, ChatGPT, ElizaOS, CrewAI, and Codex.

Remote deployment

Run a shared, multi-tenant MCP endpoint instead of a local process.

Error handling

How policy denials and API errors surface to the agent.

Getting Started

Client Integrations

Deployment

Reference

Prerequisites

Step 1: Create an Agent and get its API key

Step 2: Set your environment variables

Step 3: Connect an MCP client

Step 4: Make your first agent tool call

Step 5: Try a policy-checked payment

Next steps

Tools Reference

Choose your client

Remote deployment

Error handling

​Prerequisites

​Step 1: Create an Agent and get its API key

​Step 2: Set your environment variables

​Step 3: Connect an MCP client

​Step 4: Make your first agent tool call

​Step 5: Try a policy-checked payment

​Next steps

Tools Reference

Choose your client

Remote deployment

Error handling

Prerequisites

Step 1: Create an Agent and get its API key

Step 2: Set your environment variables

Step 3: Connect an MCP client

Step 4: Make your first agent tool call

Step 5: Try a policy-checked payment

Next steps