get_ioc_matches
AI agents call get_ioc_matches to retrieve information from Chronicle SecOps MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves indicators of compromise (IoC) matches from Chronicle's security suite, which is a read-only query operation. It does not modify, delete, or execute any actions—it simply returns matching indicators. The low severity reflects that even if misused by an AI agent, it can only expose security event data already indexed in Chronicle, without causing system changes or data loss.
From the tool's definition Tool is called 'get_ioc_matches' and is part of a Chronicle SecOps MCP server suite where sibling tools (get_security_alerts, list_security_rules, lookup_entity, search_security_events) all perform read-only security information queries.
Attacks that exploit this kind of access
get_ioc_matches. It is categorised as a Read tool in the Chronicle SecOps MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chronicle SecOps MCP Server MCP server in PolicyLayer and add a rule for get_ioc_matches: 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 Chronicle SecOps MCP Server. Nothing to install.
get_ioc_matches 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 get_ioc_matches 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 get_ioc_matches. 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.
get_ioc_matches is provided by the Chronicle SecOps MCP Server MCP server (mcpflow/mcp-secops-v3). 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 →