Web3 security, DEX honeypot detector, and DAO governance auditor for Base & EVM chains.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Stage 1 Free static bytecode scanner for honeypot indicators on DEX tokens: blacklist manipulation (isBlacklisted, setBlacklist), arbitrary transfer taxes / 100% sell fee traps, trading freeze backdoors, and selfdestruct opcodes.
Hex EVM address of token contract to inspect for honeypot traps
EVM Chain ID (8453 for Base Mainnet)
Optional raw token runtime bytecode hex string (0x...) for offline analysis
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http web3-systemic-agent https://web3-systemic-agent.onrender.com/mcp
Stage 1 Free static bytecode scanner for honeypot indicators on DEX tokens: blacklist manipulation (isBlacklisted, setBlacklist), arbitrary transfer taxes / 100% sell fee traps, trading freeze backdoors, and selfdestruct opcodes.
| Argument | Type | Description |
|---|---|---|
| chain_id | integer | EVM Chain ID (8453 for Base Mainnet) |
| token_address* | string | Hex EVM address of token contract to inspect for honeypot traps |
| bytecode_override | string | Optional raw token runtime bytecode hex string (0x...) for offline analysis |
{
"type": "object",
"required": [
"token_address"
],
"properties": {
"chain_id": {
"type": "integer",
"default": 8453,
"description": "EVM Chain ID (8453 for Base Mainnet)"
},
"token_address": {
"type": "string",
"description": "Hex EVM address of token contract to inspect for honeypot traps"
},
"bytecode_override": {
"type": "string",
"description": "Optional raw token runtime bytecode hex string (0x...) for offline analysis"
}
}
}Stage 2 Deep Semantic LLM Security and Governance Audit. Performs deterministic on-chain gatekeeping followed by structured Gemini LLM evaluation over natural language proposal claims vs bytecode and calldata reality. Requires $0.05 USDC x402 micropayment on Base Mainnet.
| Argument | Type | Description |
|---|---|---|
| calldata | string | Transaction hex calldata or function selector being executed |
| chain_id | integer | EVM Chain ID (default: 8453 for Base Mainnet) |
| policy_prompt | string | Security policy or governance criteria to audit against |
| risk_threshold | number | Risk score threshold (0.0 to 10.0) above which the audit triggers rejection or alert |
| target_address* | string | Hex EVM address of smart contract under evaluation |
| x402_payment_header | string | Optional Base64-encoded EIP-3009 transferWithAuthorization payment header satisfying $0.05 USDC requirement |
| proposal_description* | string | Natural language claim or governance proposal description explaining the intent of the transaction |
{
"type": "object",
"required": [
"target_address",
"proposal_description"
],
"properties": {
"calldata": {
"type": "string",
"default": "0x",
"description": "Transaction hex calldata or function selector being executed"
},
"chain_id": {
"type": "integer",
"default": 8453,
"description": "EVM Chain ID (default: 8453 for Base Mainnet)"
},
"policy_prompt": {
"type": "string",
"default": "Audit contract and proposal for unauthorized privilege escalation, proxy upgrades, honeypot traps, or treasury drainage.",
"description": "Security policy or governance criteria to audit against"
},
"risk_threshold": {
"type": "number",
"default": 7,
"description": "Risk score threshold (0.0 to 10.0) above which the audit triggers rejection or alert"
},
"target_address": {
"type": "string",
"description": "Hex EVM address of smart contract under evaluation"
},
"x402_payment_header": {
"type": "string",
"description": "Optional Base64-encoded EIP-3009 transferWithAuthorization payment header satisfying $0.05 USDC requirement"
},
"proposal_description": {
"type": "string",
"description": "Natural language claim or governance proposal description explaining the intent of the transaction"
}
}
}Stage 1 Free deterministic inspection of smart contract bytecode on Base or EVM chains. Discovers 4-byte function selectors and flags high-risk administrative capabilities (ownership transfer, proxy upgrade, unconstrained minting, selfdestruct).
| Argument | Type | Description |
|---|---|---|
| chain_id | integer | EVM Chain ID (8453 for Base Mainnet, 84532 for Base Sepolia, 42161 for Arbitrum One) |
| target_address* | string | Hex EVM address of smart contract to inspect (e.g. '0x4200000000000000000000000000000000000006') |
| bytecode_override | string | Optional raw contract runtime bytecode hex string (0x...) for offline analysis without RPC calls |
{
"type": "object",
"required": [
"target_address"
],
"properties": {
"chain_id": {
"type": "integer",
"default": 8453,
"description": "EVM Chain ID (8453 for Base Mainnet, 84532 for Base Sepolia, 42161 for Arbitrum One)"
},
"target_address": {
"type": "string",
"description": "Hex EVM address of smart contract to inspect (e.g. '0x4200000000000000000000000000000000000006')"
},
"bytecode_override": {
"type": "string",
"description": "Optional raw contract runtime bytecode hex string (0x...) for offline analysis without RPC calls"
}
}
}Stage 1 Free scanner for recent Snapshot DAO governance proposals (Arbitrum, Aave, ENS). Extracts on-chain target addresses and calldata execution payloads to detect governance takeover attempts and discrepancies.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum number of proposals to fetch (default: 3) |
| space_id | string | Snapshot DAO space ENS identifier (e.g., 'arbitrumfoundation.eth', 'aavedao.eth', 'ens.eth') |
| use_curated_offline | boolean | If true, returns verified realistic offline curated proposals without outbound network calls |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 3,
"description": "Maximum number of proposals to fetch (default: 3)"
},
"space_id": {
"type": "string",
"default": "arbitrumfoundation.eth",
"description": "Snapshot DAO space ENS identifier (e.g., 'arbitrumfoundation.eth', 'aavedao.eth', 'ens.eth')"
},
"use_curated_offline": {
"type": "boolean",
"default": false,
"description": "If true, returns verified realistic offline curated proposals without outbound network calls"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 9, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.