What is erc-8126-scan?

A read-only lookup service for ERC-8004 agents and their Cybercentry security scores. ERC-8004 is an on-chain registry for identifying software agents, while ERC-8126 defines the verification reports.

Searching agents, viewing registration details and activity, and reading reports covering areas such as contracts, media, web applications, and wallet screening.

It lets you review an agent’s public identity and stored security checks before trusting it. It does not perform new checks or make blockchain changes, and some calls cost USDC.

erc-8126-scan — Skill for Claude Code and Codex by Cybercentry

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Cybercentry/erc-8126-scan-mcp --skill erc-8126-scan

Clone the repo

git clone --depth 1 https://github.com/Cybercentry/erc-8126-scan-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan/github.svg)](https://agentmods.dev/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan)

Your own site

<a href="https://agentmods.dev/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan"><img src="https://agentmods.dev/badge/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan"><img src="https://agentmods.dev/badge/skills/cybercentry/erc-8126-scan-mcp/erc-8126-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01311
Opus 5	$0.00018	$0.00656
Sonnet 5	$0.00007	$0.00262
Haiku 4.5	$0.00004	$0.00131

Measured 10d ago against content hash 47beed70582f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

erc-8126-scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/erc-8126-scan/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ERC-8126 Scan

Description

A searchable index of every agent minted in the ERC-8004 Identity Registry — 378,000+ and growing — each carrying Cybercentry verification results across five dimensions: token contract, staking contract source, media provenance, web application, and wallet sanctions screening.

Use this to check another agent before interacting with it: who registered it, whether anything about it has been verified, and what was found.

The verification interface these results implement is specified in ERC-8126: AI Agent Verification (Final), co-authored by the maintainers. The agents themselves are registered under ERC-8004: Trustless Agents, whose on-chain Identity Registry is the source this index syncs from.

This server serves results already computed and stored. It does not run verifications and cannot mint, write on-chain, or spend credits. All four tools are read-only.

Privacy notice: queries name agents, wallets and UUIDs already public on chain. No private data is submitted.

Payment notice: tools cost USDC per call over x402 — $0.001 for search_agents and get_agent, $0.002 for get_agent_activity, $0.05 for get_agent_report. An erc8126_ API key is the alternative, drawing on a plan quota instead. Listing the tools is free either way.

Instructions

The server is remote, so there is nothing to install:

URL: https://erc8126scan.ai/api/mcp
Transport: streamable-http
Registry name: uk.co.cybercentry/erc-8126-scan

In OpenClaw: openclaw mcp add erc-8126-scan --url https://erc8126scan.ai/api/mcp --transport streamable-http. In Claude: Settings, Connectors, Add custom connector, paste the URL. Other MCP clients: add a remote server at the same URL.

Payment is per call in USDC over x402, on Base or Solana — no account and no key needed. Clients that speak x402 handle this automatically: an unpaid call comes back as a JSON-RPC error with code 402 carrying the price and requirements, and the client pays and retries. Alternatively pass Authorization: Bearer erc8126_... to draw on a subscription quota instead; keys come from https://erc8126scan.ai/my-api-keys.

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 118 lines · 37 tokens per session scan A 47beed70582f

Subscribe to this mod's changes

erc-8126-scan is a skill published in the GitHub repository Cybercentry/erc-8126-scan-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 37 tokens to every session and 1,311 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security Web3 and blockchain ai-agents blockchain-security erc-8004 erc-8126 mcp model-context-protocol

cybercentry-verification

Verify wallets, tokens, smart contracts, AI agents and web applications before trusting them, paying per call in USDC over x402.

Cybercentry/verification-mcp · 33 tokens

okx-cex-earn

A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.

okx/agent-trade-kit · 274 tokens

web3-bug-classes

Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.

Awarexone/web3-bug-bounty-hunting-ai-skills · 72 tokens

web3-poc-foundry

Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.

Awarexone/web3-bug-bounty-hunting-ai-skills · 59 tokens

web3-triage-report

Bug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying real examples of paid vulnerabilities.