Analyze email headers for phishing indicators
AI agents call analyze_email 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 retrieves and analyzes email header data to identify security threats (phishing, spoofing indicators). Analysis is a read-only operation with no side effects on data or systems. The severity is low because misuse would only result in false analysis reports, not exposure of sensitive data or system compromise.
From the tool's definition The tool 'analyze_email' with description 'Analyze email headers for phishing indicators' performs security analysis on email metadata. It extracts and examines header information to detect threats but does not modify, delete, execute code, or move money.
Attacks that exploit this kind of access
Analyze email headers for phishing indicators. 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 analyze_email: 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.
analyze_email 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 analyze_email 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 analyze_email. 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.
analyze_email 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 →