Before your agent approves a token or interacts with an unfamiliar contract, you need to know if it's a proxy, an EIP-7702 delegated EOA, or flagged for unlimited allowances. This server exposes two tools: check_contract() runs risk analysis on any address (contract vs EOA, upgrade patterns, ERC20 metadata) and check_approval() audits existing token allowances for the unlimited approval vector that drives most drains. It works over public JSON-RPC on Base and Ethereum with zero dependencies or signing. If you're building agents that touch DeFi, this is the pre-interaction sanity check you bolt on first. Also available as a pay-per-call x402 HTTP endpoint at $0.005 USDC.
MCP server for a pre-interaction risk check on any EVM contract/token — what an agent needs before it approves, swaps, or trusts an address.
Tool: check_contract(address, chain="base") →
Chains: Base, Ethereum. Pure public JSON-RPC, zero dependencies, no signing.
Also available as a pay-per-call x402 HTTP endpoint:
https://eltociear-contract-guard.hf.space (POST /check, $0.005 USDC on Base).
docker run -i --rm ghcr.io/eltociear/contract-guard-mcp:mcp-latest
# or
python3 server.py
MIT licensed.
check_contract(address, chain) — is-contract/EOA, EIP-7702, proxy, ERC20 metadata, risk scorecheck_approval(token, owner, spender, chain) — ERC20 allowance audit; flags unlimited approvals (the #1 drain vector)This MCP server is free (run it locally / via your client). For server-side, batch, or no-install use, the same engine is a pay-per-call x402 HTTP API — POST https://eltociear-contract-guard.hf.space/check ($0.005 USDC on Base, no signup). Your agent's wallet pays per call.