Lumen Pre-Sign Check
Use before signing an EVM tx or EIP-712 message: risk flags + verdict. Informational, no simulation
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"lumen-presign-check": {
"url": "https://lumenworks-x402-decoder.onrender.com/mcp/presign"
}
}
}Remote endpoints
https://lumenworks-x402-decoder.onrender.com/mcp/presignstreamable-httpWhat it can do
Tool inventory
Tools (2)
🟢explain_before_sign(transaction, calldata, typedData, chainId, expected_pay_to)
Lumen Pre-Sign Check. Use before signing any EVM transaction or EIP-712 message: returns {summary, flags[], verdict} with verdict looks_ok | review | do_not_sign_unless_intended. Flags unlimited approve/increaseAllowance, EIP-2612 Permit and Permit2 (typed data and on-chain), setApprovalForAll, unknown spender, admin calls (upgradeTo/transferOwnership), zero-price Seaport orders, long deadlines, chain mismatch and x402 payTo mismatch; decodes multicall/aggregate3 inner calls one level. Example: USDC approve(spender, 2^256-1) -> do_not_sign_unless_intended, UNLIMITED_APPROVAL. Agent policy: abort on do_not_sign_unless_intended, escalate review. Informational, not a security guarantee; looks_ok does not mean safe; no simulation. $0.002, no signup, free tier 20/h; not charged if the call errors.
Input Schema
{
"type": "object",
"properties": {
"transaction": {
"type": "object",
"description": "Unsigned EVM transaction",
"properties": {
"to": {
"type": "string",
"description": "Target contract/address (0x…)"
},
"data": {
"type": "string",
"description": "Calldata hex (0x…)"
},
"value": {
"type": "string",
"description": "Native value in wei (decimal string)"
}
},
"required": [
"data"
]
},
"calldata": {
"type": "string",
"description": "Shortcut: calldata hex when you have no tx object"
},
"typedData": {
"type": "object",
"description": "EIP-712 typed data {domain, types, primaryType, message} (Permit, Permit2, EIP-3009, Seaport…)"
},
"chainId": {
"type": "number",
"description": "Chain the wallet is on; used for chain-mismatch checks"
},
"expected_pay_to": {
"type": "string",
"description": "For x402/EIP-3009 payments: the payTo you expect; mismatch is flagged"
}
},
"anyOf": [
{
"required": [
"transaction"
]
},
{
"required": [
"calldata"
]
},
{
"required": [
"typedData"
]
}
]
}🟢x402_payment_safety_check(url, method, payment_required, expected_pay_to, expected_network, ...)
FREE, deterministic pre-payment check for an x402 endpoint. Give {url} (we fetch its unpaid 402) and/or {payment_required} (402 JSON or base64 header), plus optional expected_pay_to, expected_network, max_price_usdc, listed_price_usdc, facilitator_url, client_config {max_per_call_usdc, max_daily_usdc, idempotency_key, allow_any_pay_to}. Returns verdict ok/review/do_not_pay with checks: HTTPS/health, payTo validity & mismatch, unknown asset/network, price sanity vs cap/listing, timeout/replay window, multiple payTo, unknown facilitator, missing spend caps/idempotency. Nothing is stored; inputs that look like private keys are rejected.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"method": {
"type": "string",
"enum": [
"POST",
"GET"
]
},
"payment_required": {},
"expected_pay_to": {
"type": "string"
},
"expected_network": {
"type": "string"
},
"max_price_usdc": {
"type": "number"
},
"listed_price_usdc": {
"type": "number"
},
"facilitator_url": {
"type": "string"
},
"client_config": {
"type": "object"
}
}
}Community
Evidence