AI agents call search_emails to retrieve information from Bichon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries email data with no capability to modify, delete, or execute operations. It performs a search operation which is inherently a Read action. The low severity reflects that while emails may contain sensitive information, the tool only permits retrieval—not modification or destruction—and the archived nature suggests it is already a controlled data source.
From the tool's definition Tool description states it can 'search emails' and 'search...by full-text query, date range, sender, and/or mailbox folder.' These are query operations.
Attacks that exploit this kind of access
Search emails by full-text query, date range, sender, and/or mailbox folder. It is categorised as a Read tool in the Bichon MCP Server, which means it retrieves data without modifying state.
Register the Bichon MCP server in PolicyLayer and add a rule for search_emails: 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 Bichon. Nothing to install.
search_emails 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_emails 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_emails. 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_emails is provided by the Bichon MCP server (pras-labs/bichon-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 →