Gmail-style query (from:, subject:, has:attachment). Optional folder + ISO date_range.
AI agents call search_email 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.
The tool searches and retrieves email data based on filter criteria. It has no capability to modify, delete, or execute operations—it only queries existing email messages. This is a straightforward read operation with minimal blast radius even if misused by an agent, as it cannot change any state or cause financial/destructive harm.
From the tool's definition Tool description states "Gmail-style query" with search parameters like "from:", "subject:", "has:attachment" and optional filters. These are all read-only retrieval operations that query and search email data without modification.
Attacks that exploit this kind of access
Gmail-style query (from:, subject:, has:attachment). Optional folder + ISO date_range. 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 search_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 Nexus Core. Nothing to install.
search_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 search_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 search_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.
search_email 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 →