Skip to main content
Glama

Ingravity Autonomous EVM Security & DeFi Guard (x402 v2)

ERC-20 Token Honeypot & Rugpull Safety Scanner

ingravity_scanTokenRugpullAndHoneypot
Read-onlyIdempotent

Audits an ERC-20 token for honeypots, hidden mints, blacklists, abusive taxes, paused swaps, and stealth proxies using deployed tokenAddress (live 5-EVM RPC bytecode scan), pre-deploy Solidity code, or both (omitting both returns -32602). Read-only across chainId (default 8453 Base; tokenName labels the output), returning verdict, canSell, rugProbabilityScore (0-100), and PROCEED/CAUTION/ABORT. Set tier to FULL ($0.12 USDC, default) for evidence and sellSimulation, or ESSENTIAL ($0.04 USDC) for verdict scalars only; unpaid calls return isError: true (0.15% SLA or 5%-10% Safe-Harbor split applies to live-TVL rescue fixes). Use before swapping tokens; use ingravity_auditSolidityContract for general Solidity source.

Input Schema

NameRequiredDescriptionDefault
codeNoOptional Solidity (.sol) source code for pre-deployment 14-rule rugpull AST scan or hybrid source + bytecode analysis.
tierNoBilling & output depth: FULL ($0.12 USDC) returns sellSimulation, liveOnChainForensics, risk pillars, and forensicEvidence; ESSENTIAL ($0.04 USDC) returns verdict, canSell, score, and action scalars only.FULL
chainIdNoEVM Chain ID for RPC lookup when tokenAddress is supplied (8453 Base, 42161 Arbitrum, 10 Optimism, 137 Polygon, 1 Ethereum; unknown falls back to 8453).
tokenNameNoOptional token ticker or label echoed in the report.
tokenAddressNoDeployed 42-char EVM ERC-20 contract address (0x...) inspected via live RPC bytecode & proxy slots (no Solidity source required). Provide tokenAddress, code, or both.

Output Schema

NameRequiredDescriptionDefault
actionYesTrade safety gate recommendation.
signalYesTraffic-light risk indicator.
canSellYesTrue when no transfer locks, honeypot hooks, or blocking traps were detected.
chainIdYesResolved EVM chain ID.
pillarsNoBoolean breakdown across 6 rugpull pillars (FULL tier only).
settledYesWhether x402 USDC payment settled cleanly.
verdictYesOverall rugpull/honeypot verdict.
decisionYesNormalized sellability decision.
tokenNameYesResolved token name label.
tokenAddressNoInspected token address (null when scanning pre-deploy code only).
inspectionModeYesWhether inspection used live RPC bytecode, static Solidity AST, or hybrid.
sellSimulationNoSimulated sellability and liquidity-lock indicators (FULL tier only).
forensicEvidenceNoMatched AST and bytecode rules with snippets (FULL tier only).
isHoneypotLikelyYesTrue if explicit sell-blocking or honeypot trap signatures matched.
rugProbabilityScoreYesWeighted rugpull risk score from 0 to 100.
liveOnChainForensicsNoLive RPC bytecode size, proxy implementation, owner status, and pause state (FULL tier only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), yet the description adds substantive behavior: tiered billing prices, that unpaid calls return isError: true, and that FULL includes sellSimulation/forensic evidence while ESSENTIAL returns scalars only. The SLA/Safe-Harbor sentence is opaque jargon that an agent cannot act on, which keeps this from a 5.

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

Conciseness3/5

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

Front-loaded and information-dense, but the single paragraph is a run-on bundling input modes, pricing, error codes, return fields, and an SLA clause. The trailing '0.15% SLA or 5%-10% Safe-Harbor split' parenthetical is contractual fine print that does not help an agent decide or invoke, and dilutes the actionable content.

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

Completeness4/5

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

For a 5-parameter read-only scanner with full schema coverage and an output schema, this covers the essentials: input modes, chain scope, tier trade-off, cost, failure behavior, and the action verdicts. Return-value explanation is redundant given the output schema, and the SLA language is noise, but nothing an agent needs to call it correctly is missing.

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 is 3; the description still adds meaning by tying tier to output depth and cost, restating the chainId default and fallback to 8453, and clarifying that omitting both inputs is an error rather than a valid call. Most of this is reinforcement of schema text rather than new information, so it does not reach 5.

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

Purpose5/5

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

The description opens with a specific verb and resource ('Audits an ERC-20 token') and enumerates the exact threat classes checked: honeypots, hidden mints, blacklists, abusive taxes, paused swaps, stealth proxies. It also names the sibling it is not ('use ingravity_auditSolidityContract for general Solidity source'), so an agent can route between the two without reading either schema.

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

Usage Guidelines5/5

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

Explicit when-to-use ('Use before swapping tokens') plus an explicit alternative for the adjacent case (general Solidity source audits). It also states the input precondition clearly: provide tokenAddress, code, or both, with the failure mode (-32602) when neither is supplied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.