get_my_emails
AI agents call get_my_emails to retrieve information from Cryptosense without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a retrieval operation ('get_my_emails'), which aligns with the Read category. However, empty description significantly reduces confidence. Low severity assumes the worst case is unauthorized email access, not system-wide compromise. The tool name alone is insufficient for high confidence classification.
From the tool's definition Tool name 'get_my_emails' suggests retrieval of email data with no modification. However, the description is empty, making classification uncertain. The tool appears to retrieve user emails (read operation) rather than modify, delete, or execute actions.
Attacks that exploit this kind of access
get_my_emails. It is categorised as a Read tool in the Cryptosense MCP Server, which means it retrieves data without modifying state.
Register the Cryptosense MCP server in PolicyLayer and add a rule for get_my_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 Cryptosense. Nothing to install.
get_my_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 get_my_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 get_my_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.
get_my_emails is provided by the Cryptosense MCP server (josephibra/cryptosense-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 →