Check if a blockchain address is flagged as malicious.
AI agents call check_malicious_address to retrieve information from Tatum MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only lookup against a malicious address database or service. It queries existing data to determine if an address has been flagged, with no side effects, state changes, or destructive operations. Even in a misuse scenario, an agent could only retrieve information about addresses, posing minimal risk.
From the tool's definition Tool name 'check_malicious_address' and description 'Check if a blockchain address is flagged as malicious' indicate a query/lookup operation that retrieves status information about an address.
Documented attack patterns abuse exactly the kind of access check_malicious_address gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tatum MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for check_malicious_address:
{
"version": "1",
"default": "deny",
"tools": {
"check_malicious_address": {}
}
}check_malicious_address is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check if a blockchain address is flagged as malicious. It is categorised as a Read tool in the Tatum MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tatum MCP Server MCP server in PolicyLayer and add a rule for check_malicious_address: 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 Tatum MCP Server. Nothing to install.
check_malicious_address 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 check_malicious_address 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 check_malicious_address. 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.
check_malicious_address is provided by the Tatum MCP Server MCP server (tatumio/blockchain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tatum MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Tatum MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.