Ingravity EVM Security MCP

by dev.workers.daviddelmoral79.red-shape-1b3b

ingravity_auditSolidityContract

Unlocks deterministic PROCEED/ABORT signal & forensic report: Deterministic 24-Vector Solidity Audit, Fixes & Safe-Harbor Guard ($0.85 Floor / $0.35 Signal + Optional 0.15% SLA or 5%-10% Live Rescue Split) (Paid via x402 v2 on Base Mainnet eip155:8453 — Full Report: $0.85 USDC | Signal Only Fast Verdict: $0.35 USDC).

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": {
      "code": "<code>"
    },
    "name": "ingravity_auditSolidityContract"
  }
}

Input Schema

Name	Required	Description
`code`	Yes	Raw Solidity (.sol) smart contract source code to audit
`contractName`	No	Optional contract identifier
`ownerTreasury`	No	Optional protocol owner/multisig recipient (0x...) for 90%-95% rescued capital
`contractAddress`	No	Optional deployed Base Mainnet contract address (0x...) for live RPC liquidity verification & Safe-Harbor rescue calldata

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

C2.7/5.0

Behavior3/5

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

No annotations exist, so the description carries the full burden. It does disclose two genuinely important behaviors: the tool is paid via x402 v2 on Base Mainnet (eip155:8453) and output is deterministic with two price tiers ($0.85 full report, $0.35 signal-only) plus optional percentage-based charges. It does not explain what the optional 'SLA' or 'Live Rescue Split' actually obligate, whether payment happens before or during the call, or what a caller does when payment fails.

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

Conciseness2/5

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

It is one run-on sentence that repeats the pricing three times ($0.85 appears twice, $0.35 twice, plus percentages and an SLA split). The useful front-load ('Unlocks deterministic PROCEED/ABORT signal & forensic report') is immediately buried under payment boilerplate, making the operational content hard to extract.

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

Completeness3/5

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

For a paid, stateful-feeling audit tool with four parameters and no output schema, the definition covers payment mechanics reasonably but omits the optional parameters' effects and never characterizes the report contents beyond 'forensic report'. An agent could invoke it with only 'code', but would not know what the optional fields change or what a returned verdict looks like.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all four parameters and the baseline is 3. The description adds no parameter-level meaning at all — contractName, ownerTreasury, and contractAddress are never mentioned, and the 'Live Rescue Split' / 'Safe-Harbor' language only faintly implies that contractAddress unlocks live RPC verification and that ownerTreasury receives rescued capital.

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

Purpose3/5

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

The description does name the resource and operation ('Deterministic 24-Vector Solidity Audit') and the deliverable ('PROCEED/ABORT signal & forensic report'), so the core purpose is recoverable. However it is wrapped in unexplained jargon ('24-Vector', 'Safe-Harbor Guard', 'Live Rescue Split') and gives no differentiation from siblings like ingravity_scanTokenRugpullAndHoneypot or ingravity_simulateDeepExploitAndWhitehatBounty. An agent must already know what a '24-vector audit' is to act on this.

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

Usage Guidelines2/5

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

There is no when-to-use / when-not-to-use guidance and no named alternatives among the six sibling tools. The only implicit selection cue is the price tier list (full report vs signal-only fast verdict), which hints at a cheap triage mode but never states a condition for choosing it. The agent is left to infer everything about routing.

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

All Ingravity EVM Security MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?