AI agents call search_malware to retrieve information from OpenCTI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves malware intelligence records from OpenCTI without modifying, executing code, deleting data, or committing financial transactions. It is a purely informational query operation with no side effects. The blast radius of misuse is minimal—an agent could retrieve sensitive threat intel, but cannot cause irreversible harm, execute arbitrary operations, or affect external systems.
From the tool's definition Tool name 'search_malware' and description '搜尋OpenCTI中的惡意程式' (Search for malware in OpenCTI) indicate a query/search operation that retrieves threat intelligence data.
Documented attack patterns abuse exactly the kind of access search_malware gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCTI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_malware:
{
"version": "1",
"default": "deny",
"tools": {
"search_malware": {}
}
}search_malware 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.
搜尋OpenCTI中的惡意程式. It is categorised as a Read tool in the OpenCTI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCTI MCP Server MCP server in PolicyLayer and add a rule for search_malware: 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 OpenCTI MCP Server. Nothing to install.
search_malware 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 search_malware 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 search_malware. 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.
search_malware is provided by the OpenCTI MCP Server MCP server (zxzinn/opencti-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 OpenCTI MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 OpenCTI MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.