AI agents call get_email 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 exclusively reads/retrieves email data without side effects. It queries archived email content and returns it to the user. The description explicitly states it 'Get[s]' content (a retrieval operation), not create/modify/delete. Combined with sibling tools (search_emails, list_threads, list_mailboxes) all being read-only queries, this is clearly a Read operation with low severity.
From the tool's definition Tool retrieves and returns 'full plain-text content of an email' from locally-archived emails. No modification, deletion, or execution capability described. Parameters (account_id, envelope_id) are references obtained from search results.
Attacks that exploit this kind of access
Get full plain-text content of an email. account_id and envelope_id come from search_emails results. 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 get_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 Bichon. Nothing to install.
get_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 get_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 get_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.
get_email 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 →