Recent calendar events + Gmail messages involving this contact's email addresses.
AI agents call recent_interactions 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 read-only access to calendar and email data. It queries and returns historical information without creating, modifying, deleting, or executing any operations. The blast radius of misuse is limited to information disclosure about a contact's interactions.
From the tool's definition Tool description states it retrieves 'Recent calendar events + Gmail messages' — purely informational queries with no modification or action. The verb 'involving' indicates passive retrieval/filtering of existing data.
Attacks that exploit this kind of access
Recent calendar events + Gmail messages involving this contact's email addresses. 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 recent_interactions: 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.
recent_interactions 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 recent_interactions 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 recent_interactions. 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.
recent_interactions 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 →