@true402.dev/mcp-server

address_safety

Structural safety profile for ANY Base address — an EOA or an arbitrary contract — before an agent sends funds to it, approves it, or calls it.

Instructions

Structural safety profile for ANY Base address — an EOA or an arbitrary contract — before an agent sends funds to it, approves it, or calls it. Returns contract-vs-EOA, ETH + USDC balance, tx-count (activity), and for contracts: whether it is a recognised ERC-20, ownership state, a mint() selector, and whether it is an EIP-1967 upgradeable proxy (its logic can be swapped after you trust it). Coarse risk band + flags. On-chain reads only — no API key. POST { address }. Unpaid: free while the caller's IP has free-trial calls left that day (a small daily allowance shared across the trial stalls, no wallet); otherwise returns 402. (PAID x402 service — USDC on Base; the MCP server needs a funded wallet to settle.) Price: $0.005 USD (fixed).

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": {
      "address": "<address>"
    },
    "name": "address_safety"
  }
}

Input Schema

Name	Required	Description	Default
`chain`	No	Chain to check; only 'base' is supported (default)
`address`	Yes	Any address (0x…) on Base — an EOA or a contract

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.0Jun 28, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With zero annotations, the description carries the full burden and does so: it discloses that this is an on-chain-read-only, no-API-key operation, that a free daily trial exists and returns 402 when exhausted, and that the service is a paid x402 endpoint at a fixed $0.005. It even flags the trust caveat that an EIP-1967 proxy's logic can be swapped after inspection, which is exactly the kind of risk context an agent needs.

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-loads the purpose and the when-to-use trigger, then packs returns, risk band, and payment model into a compact block. The parenthetical payment/free-trial sentence is dense but earns its place for a metered paid service; a slight trimming of nested parentheses would tighten it.

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?

No output schema exists, so the description must describe returns — and it does, at field granularity. Combined with the cost, payment-failure, and free-trial behavior, an agent has everything needed to decide whether and how to call it without further guessing.

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 coverage is 100% and both parameters (address, chain) are already documented in the schema, including the Base-only constraint. The description reinforces 'any address, EOA or contract' and the POST body shape, but adds no syntax or format detail beyond structured data, so baseline 3 applies.

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?

States a specific verb and resource — a structural safety profile for any Base address, EOA or contract — and names the decision it supports (send, approve, call). It also enumerates the exact outputs (contract-vs-EOA, ETH/USDC balance, tx-count, ERC-20 recognition, ownership, mint() selector, EIP-1967 proxy), which lets an agent distinguish it from siblings like token_safety or address_risk.

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

Usage Guidelines4/5

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

Gives a concrete trigger: check before sending funds to, approving, or calling an address. The Base-only scoping implicitly routes other chains to address_safety_ethereum/address_safety_bsc, but no alternative tool is named explicitly as the choice for a different chain or for a token-level versus address-level check.

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