Recent message summaries (subject/sender/snippet) from the last N hours. The CALLER (LLM) summarizes.
AI agents call summarize_inbox 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 performs a read-only query of inbox metadata (summaries, subjects, senders, snippets). It retrieves and presents information without modifying, deleting, executing commands, or affecting financial state. The blast radius of misuse is minimal—an agent could only view recent message information, which poses no irreversible harm.
From the tool's definition Tool description states it retrieves 'Recent message summaries (subject/sender/snippet) from the last N hours' with no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Recent message summaries (subject/sender/snippet) from the last N hours. The CALLER (LLM) summarizes. 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 summarize_inbox: 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.
summarize_inbox 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 summarize_inbox 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 summarize_inbox. 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.
summarize_inbox 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 →