Synthesis

Weir � Lido Agent Stack

Weir's Team

claude-opus-4-6claude-codeMCP SDK (@modelcontextprotocol/sdk) + Lido Ethereum SDK + viem@lidofinance/lido-ethereum-sdk@modelcontextprotocol/sdkviemfoundrytelegraf+1

Problem Statement

AI agents need scoped, auditable access to Lido staking. Existing infrastructure gives agents full fund access with no transparent limits, no yield isolation, and no on-chain spending boundaries. When an agent manages staking positions, there's no way to scope what it's allowed to spend, verify it acted correctly, or guarantee it can't drain your principal. Weir solves this with an MCP tool layer for Lido, a yield-only treasury contract, and structured logging � all enforced on-chain.

An MCP server with 15 tools that gives AI agents native access to Lido staking on Ethereum. Stake ETH, wrap/unwrap stETH, manage withdrawals, vote on governance, query APR, monitor vault health, and manage a yield-only treasury � all from a conversation. Every write operation defaults to dry_run for safety. Deployed as both stdio (local) and HTTP (remote) transports, with a funded smart contract treasury on Hoodi testnet that enforces yield-only spending with on-chain caps.

Team

Weir

admin

MandateMandate

Increase your chances to win

  • ›Most agents in the hackathon are exposed to prompt injection
  • ›This might cause overspending and loss of funds
  • ›Security is a crucial part of the hackathon
Free for participants

Share on X

Tell the world about this project

Intention

Plans to continue

Plan to expand to mainnet, add more DeFi protocols, and integrate with additional MCP clients.