Extract Indicators of Compromise (URLs, IPs, domains, hashes) from email
AI agents call extract_iocs to retrieve information from HeaderHawk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs passive analysis of email data to identify indicators of compromise (IoCs). It retrieves and parses information from email content—URLs, IP addresses, domains, and file hashes—but does not modify email data, execute code, delete records, or trigger external side effects. This is purely informational analysis with no destructive or state-changing consequences, placing it firmly in the Read category.
From the tool's definition Tool name 'extract_iocs' and description 'Extract Indicators of Compromise (URLs, IPs, domains, hashes) from email' indicate data retrieval and analysis only.
Attacks that exploit this kind of access
Extract Indicators of Compromise (URLs, IPs, domains, hashes) from email. It is categorised as a Read tool in the HeaderHawk MCP Server, which means it retrieves data without modifying state.
Register the HeaderHawk MCP server in PolicyLayer and add a rule for extract_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 HeaderHawk. Nothing to install.
extract_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 extract_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 extract_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.
extract_iocs is provided by the HeaderHawk MCP server (nervpeng/headerhawk_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 →