Return the email body + key headers so the calling LLM can extract action items.
AI agents call parse_email_for_action_items to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns existing email data (body and headers) for the purpose of analysis. It performs no writes, executions, deletions, or financial operations. The LLM extracts action items from the returned data, but the tool itself only fetches and returns information.
From the tool's definition 'Return the email body + key headers so the calling LLM can extract action items' — purely retrieves and surfaces email content with no side effects
Attacks that exploit this kind of access
Return the email body + key headers so the calling LLM can extract action items. It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for parse_email_for_action_items: 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 Nexus Core. Nothing to install.
parse_email_for_action_items 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 parse_email_for_action_items 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 parse_email_for_action_items. 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.
parse_email_for_action_items is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →