AI Agents That Execute On-Chain: A Practical Guide

Why This Is Different Now

Previous AI + blockchain integrations were read-only: summarise a wallet, explain a transaction. Now, with tool-calling and MCP-connected agents, an AI can actually execute.

The Core Architecture

The signing layer is the critical piece. You have three options:

1. MPC Wallet — agent holds a key share, human approval required for full sig
2. Smart Contract Wallet (AA) — policy rules encoded on-chain, agent operates within limits
3. Custodian API — Fireblocks/BitGo with policy engine, agent submits, human approves

Safety Constraints You Must Implement

• Whitelist of allowed contracts (no arbitrary calls)
• Max transaction value per call
• Rate limiting (N transactions per hour)
• Human-in-the-loop for anything above threshold

A Real Pattern: DeFi Position Manager

An agent that monitors a Uniswap LP position and rebalances when out of range:

1. Agent reads pool state via ethers.js tool
2. Computes rebalance params
3. Constructs UserOperation (ERC-4337)
4. Submits to approval queue — human approves or auto-approves if within policy
5. Bundler submits to EntryPoint

The key insight: the agent never holds the private key. The policy engine does the authorisation.