AI agents call search-attributes to retrieve information from Security Infrastructure MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'search-attributes' combined with the context of security platform integrations (SIEM, EDR, threat intelligence) strongly indicates this retrieves or queries security attributes or metadata rather than executing commands, modifying data, or causing destructive actions. The lack of action verbs (delete, execute, run) and alignment with sibling search tools supports Read classification.
From the tool's definition Tool name 'search-attributes' indicates a retrieval/query operation. Description is empty, limiting certainty.
Documented attack patterns abuse exactly the kind of access search-attributes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Security Infrastructure MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search-attributes:
{
"version": "1",
"default": "deny",
"tools": {
"search-attributes": {}
}
}search-attributes 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.
search-attributes. It is categorised as a Read tool in the Security Infrastructure MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Security Infrastructure MCP Server MCP server in PolicyLayer and add a rule for 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 Security Infrastructure MCP Server. Nothing to install.
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 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 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.
search-attributes is provided by the Security Infrastructure MCP Server MCP server (jmstar85/securityinfrastructure). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Security Infrastructure 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.
3 Security Infrastructure MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.