AI agents call misp_search_attributes to retrieve information from Misp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search operation to retrieve threat intelligence indicators (IOCs) from MISP events. Search and query operations are Read category as they only retrieve information without creating, modifying, deleting, or executing external actions. The blast radius of misuse is low since an attacker gaining access to this tool can only view existing intelligence data, not alter or act upon it.
From the tool's definition Tool name is 'misp_search_attributes' and description states 'Search for specific attributes (IOCs) across all MISP events' — this is a query/search operation that retrieves data with no side effects.
Attacks that exploit this kind of access
Search for specific attributes (IOCs) across all MISP events. It is categorised as a Read tool in the Misp MCP Server, which means it retrieves data without modifying state.
Register the Misp MCP server in PolicyLayer and add a rule for misp_search_attributes: 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 Misp. Nothing to install.
misp_search_attributes 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_attributes 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_attributes. 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_attributes is provided by the Misp MCP server (solomonneas/misp-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 →