Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Cybercentry MCP Server Check this wallet address for sanctions and risk: 0xAbC123..."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Pay-per-call security verification for AI agents: wallets, tokens, contracts, dApps, agents and more.
Nothing to install. This is a remote MCP server — connect to the URL and the tools appear.
Endpoint |
|
Transport |
|
Registry | |
Website |
Remote servers are added as connectors, not through claude_desktop_config.json — that file is for local servers that run a command.
Settings → Connectors
Add → Add custom connector
Paste https://centry.cybercentry.co.uk/api/mcp
Anything that speaks MCP over streamable HTTP can connect. Point it at:
https://centry.cybercentry.co.uk/api/mcpCheck 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.
Related MCP server: ShieldAPI MCP
Twelve tools. Two are free and need no payment, credentials or account:
Tool | What it does |
| The catalogue: every verification, its inputs and its price |
| Live exploit feed, curated from DefiLlama |
The other ten are paid, at $1.00 per call:
Tool | What it verifies |
| Sanctions screening and risk scoring across 35 EVM chains |
| Base B20 tokens: honeypots, freeze-and-seize, pause, impersonation |
| Ethereum token due diligence |
| Solidity source, for known vulnerability classes |
| Live site and dApp frontend scan |
| An agent's configuration: auth gaps, prompt-injection exposure, unsafe permissions |
| C2PA provenance and content authenticity |
| Zero-knowledge proof over a payload, without revealing it |
| Quantum-resistant encryption of a payload |
| Advisory answers grounded in a security body of knowledge |
Wallet and web application verification return a job immediately and fill in as findings arrive; both can take up to three minutes. The rest return in under ten seconds.
No API keys. No accounts. Two ways to pay for the ten paid tools:
x402 — the client is told the price, pays in USDC, and retries. Automatic in clients that support it.
Base eip155:8453 USDC
Solana mainnet USDCSubscription token — for clients that do not speak x402 yet. Pass subscription_token as a tool argument, or send it as the x-subscription-token header.
A paid call runs the verification before it settles, so a call that fails is never charged.
The interfaces these services implement were specified in public:
ERC-8126 — AI Agent Verification (Final)
ERC-8196 — AI Agent Authenticated Wallet (Final)
ERC-8376 — Token Launch Abuse Detection and Remediation (open pull request)
Endpoint — https://centry.cybercentry.co.uk/api/mcp
Site and full catalogue — https://centry.cybercentry.co.uk
How it works — https://centry.cybercentry.co.uk/guide
Standards — https://centry.cybercentry.co.uk/standards
Cybercentry Limited
This server cannot be deployed
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
Read-only smart-contract security intelligence for autonomous agents.
Verified, pay-per-use API tools for AI agents through one authenticated connection.
