ERC-8126 Scan MCP Server

MCP serverSecurity

erc-8126-scan connects your AI to a database of 378k+ ERC-8004 agents and their security verifications. Once added, your AI can look up agents and check their verification records before you rely on them. Two tools are free to use and the rest are paid in USDC.

Use ERC-8126 Scan MCP Server in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add ERC-8126 Scan MCP Server and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use ERC-8126 Scan MCP Server to list services

Details

Available today. Use it from your connected AI after setup.

Add the integration and ask your AI to look up an agent you want to check. Start with the two free tools, since the remaining ones are billed in USDC.

ERC-8126 Scan MCP ServerStart free

What your AI can do with it

  • Look up any of the 378k+ ERC-8004 agents in the database
  • Retrieve the security verification records for a listed agent
  • Check an agent's verification status before interacting with it
  • Use the two free tools at no cost, with the remaining tools billed in USDC

Install ERC-8126 Scan MCP Server

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user erc-8126-scan-mcp-server 'https://erc8126scan.ai/api/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://erc8126scan.ai/api/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=erc-8126-scan-mcp-server&config=eyJ1cmwiOiJodHRwczovL2VyYzgxMjZzY2FuLmFpL2FwaS9tY3AifQ==

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://erc8126scan.ai/api/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add erc-8126-scan-mcp-server --url 'https://erc8126scan.ai/api/mcp'

    Run it once, then sign in with codex mcp login erc-8126-scan-mcp-server if the server asks for an account.

From the project's README

As published by cybercentry/erc-8126-scan-mcp in README.md.

Security intelligence for ERC-8004 agents: search the on-chain agent index and read verification results.

Nothing to install. This is a remote MCP server — connect to the URL and the tools appear.

Endpointhttps://erc8126scan.ai/api/mcp
Transportstreamable-http
Registryuk.co.cybercentry/erc-8126-scan
Websitehttps://erc8126scan.ai

What it is

Every agent minted in the ERC-8004 Identity Registry is indexed automatically — 378,000+ and counting. Each one carries verification results across five dimensions, produced by the Cybercentry verification services:

DimensionWhat it covers
ETVToken verificationThe agent's token contract
SCVSolidity code verificationThe staking contract source
MCVMedia content verificationC2PA provenance of the agent's image
WAVWeb application verificationThe agent's live site or dApp frontend
WVWallet verificationOFAC sanctions screening and funding-chain risk

This server exposes that index. It does not run verifications — it serves results already computed and stored.

Connect

Claude (Desktop or claude.ai)

Remote servers are added as connectors, not through claude_desktop_config.json — that file is for local servers that run a command.

  1. Settings → Connectors
  2. Add → Add custom connector
  3. Paste https://erc8126scan.ai/api/mcp

Other clients

Anything that speaks MCP over streamable HTTP can connect. Point it at:

https://erc8126scan.ai/api/mcp

Check your client's own documentation for where a remote MCP server URL goes — some use a settings pane, some a config file. If yours takes a config file, the field is the server URL rather than a command.

Tools

Six tools, all read-only. None of them mints, writes on-chain, or spends your credits.

Two are free — no payment, wallet or account:

ToolWhat it returns
list_servicesThe catalogue: every tool, its price, and how to read the risk fields
get_index_statsHow many agents are indexed, so you can judge coverage before paying

The other four are paid:

ToolWhat it returnsPer callPlan
search_agentsFilter the index by chain, risk score range and verification status; paginated$0.001Starter
get_agentFull detail for one agent by UUID$0.001Starter
get_agent_activityOn-chain activity and liveness for one agent$0.002Starter
get_agent_reportFull security assessment: per-dimension findings and evidence$0.05Pro

Call list_services first. It is free, and authoritative about current pricing.

get_agent_report returns data only for agents owned by the wallet bound to your API key. Other agents return FORBIDDEN_NOT_OWNER. Public scores for any agent are available through get_agent.

Tools you cannot reach on your plan are hidden from tools/list rather than listed and refused.

Reading the scores

Judge an agent by risk_level, not overall_risk_score.

Scoring presumes risk: a check that applies to an agent but has not been verified counts as 100. So an agent nobody has paid to assess scores exactly the same as one assessed and found dangerous. Most of the index is the former.

risk_level separates them:

ValueMeaning
not_verifiedNobody has assessed this agent yet. Not a finding against it.
not_assessedNo score recorded
low / moderate / elevated / highVerified, scoring in that band
criticalVerified and genuinely high risk

Treating a not_verified agent as dangerous is the most common way to misread this data.

Paying

Two free tools, then two ways to pay for the rest. tools/list is public, so an agent can see everything on offer and what it costs before deciding to pay for anything.

x402 — no account, no key. The client is quoted a price, pays in USDC, and retries. Pay on whichever chain you hold funds on:

Base     eip155:8453    USDC
Solana   mainnet        USDC
ToolPer call
list_servicesfree
get_index_statsfree
search_agents$0.001
get_agent$0.001
get_agent_activity$0.002
get_agent_report$0.05

An unpaid call returns a JSON-RPC error with code 402, carrying the payment requirements in error.data — the same shape as the Cybercentry verification server.

API key — for volume, or clients that do not speak x402 yet. Pass an erc8126_ key as a bearer token:

Authorization: Bearer erc8126_...

Keys come from erc8126scan.ai/my-api-keys. Calls draw on your plan's daily quota instead of being paid for individually, and tool availability and page sizes follow your tier. A key that is presented but invalid is rejected outright rather than quietly falling back to per-call billing.

Either way, get_agent_report is scoped to agents owned by the caller — the wallet bound to your key, or the wallet that paid.

Standards

  • ERC-8004 — Trustless Agents, the Identity Registry this index reads
  • ERC-8126 — AI Agent Verification (Final)
  • ERC-8196 — AI Agent Authenticated Wallet (Final)

Links


Cybercentry Limited

Tools it offers (6)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • list_services
  • get_index_stats
  • search_agents
  • get_agent
  • get_agent_activity
  • get_agent_report

Signals

Last commit
Aug 2026
Advanced
Delivery
erc-8126-scan MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
uk-co-cybercentry-erc-8126-scan
Source
github.com/cybercentry/erc-8126-scan-mcp
Hosted endpoint
https://erc8126scan.ai/api/mcp