AI agents use misp_add_event to create or update resources in Zeek — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zeek environment.
This tool performs data creation in an external system (MISP - Malware Information Sharing Platform). While creating intelligence records is constructive in a security context, from a capability perspective it is a Write action because it adds new structured data that can be modified or removed. It does not execute arbitrary code, delete data permanently, or move financial resources.
From the tool's definition Tool creates a MISP event from NIDS findings, which is a reversible write operation that adds threat intelligence data to a MISP instance.
Attacks that exploit this kind of access
Create a MISP event from NIDS findings to share threat intelligence. Includes attributes (IOCs), tags, and threat level classification. It is categorised as a Write tool in the Zeek MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zeek MCP server in PolicyLayer and add a rule for misp_add_event: 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_add_event is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the misp_add_event 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_add_event. 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_add_event 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 →