web3-agent

check_token_honeypot

Read-onlyIdempotent

Scans DEX token bytecode for honeypot traps like blacklist functions, sell taxes, trading pauses, and self-destruct opcodes, then returns a risk score and recommendation.

Instructions

Stage 1 Free ($0.00) static DEX token bytecode scanner that detects blacklist traps (isBlacklisted, setBlacklist), 100% sell-tax modifiers (setTax, setFee), trading freezes (pause), and SELFDESTRUCT opcodes. Fetches live token_address bytecode on chain_id unless bytecode_override (0x hex) is provided for offline execution; returns safe EOA status if bytecode is empty. Returns JSON with is_contract, is_honeypot_suspect (bool), risk_score (0.0-10.0), threat_categories, risk_flags, and recommendation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "token_address": "<token_address>"
    },
    "name": "check_token_honeypot"
  }
}

Input Schema

Name	Required	Description
`chain_id`	No	EVM Chain ID (8453 for Base Mainnet)
`token_address`	Yes	Hex EVM address of token contract to inspect for honeypot traps
`bytecode_override`	No	Optional raw token runtime bytecode hex string (0x...) for offline analysis

Output Schema

Name	Required	Description	Default
`tool`	No
`stage`	No
`chain_id`	No
`cost_usd`	No
`risk_flags`	Yes
`risk_score`	Yes
`is_contract`	No
`token_address`	Yes
`recommendation`	No
`threat_categories`	Yes
`bytecode_size_bytes`	No
`is_honeypot_suspect`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.1Nov 11, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "bytecode_size_bytes": {
+      "type": "integer"
+    },
+    "chain_id": {
+      "type": "integer"
+    },
+    "cost_usd": {
+      "type": "number"
+    },
+    "is_contract": {
+      "type": "boolean"
+    },
+    "is_honeypot_suspect": {
+      "type": "boolean"
+    },
+    "recommendation": {
+      "type": "string"
+    },
+    "risk_flags": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "risk_score": {
+      "type": "number"
+    },
+    "stage": {
+      "type": "integer"
+    },
+    "threat_categories": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "token_address": {
+      "type": "string"
+    },
+    "tool": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "token_address",
+    "is_honeypot_suspect",
+    "risk_score",
+    "threat_categories",
+    "risk_flags"
+  ],
+  "type": "object"
+}

First observedv0.1.0Nov 11, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds genuinely new behavior: live bytecode fetching keyed on chain_id, the offline fallback, the EOA/safe short-circuit when bytecode is empty, and a zero-cost tier — all useful and not derivable from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with tier, cost, and tool type, then detection targets, then runtime behavior, then return shape. Dense but every clause carries information; the detection list is long but each item is a distinct capability rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter read-only scanner with an output schema, this covers everything material: fetch vs offline mode, the empty-bytecode edge case, cost tier, and the key result fields. An agent could call it correctly and interpret the response without further information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3, but the description adds real semantics beyond the schema by clarifying the interaction between chain_id and bytecode_override (fetch live unless an override is supplied for offline execution). token_address is characterized as the contract to inspect; nothing important is left ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('static DEX token bytecode scanner') and enumerates exactly which trap classes it detects (blacklist, 100% sell-tax, pause, SELFDESTRUCT). It implicitly separates itself from a deeper audit via the 'Stage 1 Free ($0.00)' framing, but never names a sibling, so the differentiation is inferential rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Stage 1 Free' and 'static bytecode' framing implies this is a cheap first-pass screen before a deeper audit, and it explains the offline path via bytecode_override. However, it never states when to escalate to deep_semantic_audit or scan_contract_selectors, nor any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server