Assess the risk level of a blockchain address. Use this when you need to evaluate the risk associated with a specific wallet address, such as before accepting funds from or sending funds to an address. Supported Chains (Full Query): BTC(0), ETH(1), BSC(56), Tron(79), Polygon(137), Avalanche(43114...
Risk signalsHandles credentials or secrets (token)
Part of the Kyt server.
Free to start. No card required.
AI agents call get_address_risk to retrieve information from Kyt without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_address_risk only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_address_risk": {}
}
}See the full Kyt policy for all 3 tools.
These attack patterns abuse exactly the kind of access get_address_risk gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Assess the risk level of a blockchain address. Use this when you need to evaluate the risk associated with a specific wallet address, such as before accepting funds from or sending funds to an address. Supported Chains (Full Query): BTC(0), ETH(1), BSC(56), Tron(79), Polygon(137), Avalanche(43114), Arbitrum(42161), Optimism(10), LTC(227), Aptos(aptos), Kaia(8217), Solana(solana), TON(ton), XRP(xrp), Zksync(324), IoTeX(4689), Hsk(177) Supported Chains (Basic Query): Merlin(4200), Neo(888), Zklink(810180), Scroll(534352), Ronin(2020), Linea(59144), Berachain(80084), Monad(monad), Astar(592), Taiko(167000), Bitlayer(200901), Over(54176), Aleo(aleo), Avail(avail), Kaspa(kaspa), Movement(movement), Sui(sui), Kroma(255), Base(8453), Tao(tao), ZRC(48900), TIA(tia), Peaq(peaq), Supra(6), Arweave(arweave), Sei(1329), Wemix(1111), Eos(17777), Lumia(994873017), Viction(88), AO(ao), Story(1514), Autonomys(autonomys), Sonic(146), Nillion(nillion), Babylon(babylon), KCC(321), Initia(initia), Memecore(4352), Conflux(1030), 0G(16661), Plasma(9745) Risk Types: Darknet Market, Fraud Shop, Gambling, High Risk Exchange, High Risk Jurisdiction-FATF, Official Freeze, Phishing, Hacker, SANCTIONS, Ransomware, Scam, Bridge, NFT Trade, Stakeute, Mixer, Defi, CEX, Unnamed Entity. Token Parameter: You can pass token name (e.g., "USDT", "Tether USDt"), symbol (e.g., "SHIB", "LINK"), or contract address. The system automatically resolves it to the correct contract address based on the chain. Use empty string "" for native token analysis (e.g., ETH on Ethereum, TRX on Tron). Omit parameter for full multi-token analysis. Returns: risk scores (0-100), risk levels (Severe/High/Medium/Low), incoming/outgoing fund analysis with entity details, hop counts, and exposure types (Direct/Indirect).. It is categorised as a Read tool in the Kyt MCP Server, which means it retrieves data without modifying state.
Register the Kyt MCP server in PolicyLayer and add a rule for get_address_risk: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kyt. Nothing to install.
get_address_risk is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_address_risk rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_address_risk. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_address_risk is provided by the Kyt MCP server (@starstar214/kyt-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Kyt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.