AI agents call misp_search_iocs to retrieve information from Zeek without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a MISP threat intelligence database to retrieve information about indicators of compromise. No creation, modification, deletion, or execution of code/commands occurs. The worst-case misuse would be unauthorized reconnaissance of threat data, which has limited blast radius compared to Write, Execute, or Destructive actions.
From the tool's definition Tool performs searches and lookups ('Search MISP', 'Look up') against observables with no modification or deletion operations described. The description explicitly lists query operations (search, lookup) with no side effects mentioned.
Attacks that exploit this kind of access
Search MISP for indicators of compromise (IOCs). Look up IPs, domains, hashes, URLs, and other observables against MISP. It is categorised as a Read tool in the Zeek MCP Server, which means it retrieves data without modifying state.
Register the Zeek MCP server in PolicyLayer and add a rule for misp_search_iocs: 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 Zeek. Nothing to install.
misp_search_iocs 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 misp_search_iocs 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 misp_search_iocs. 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.
misp_search_iocs is provided by the Zeek MCP server (solomonneas/zeek-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →