AI agents call capture_email_code to retrieve information from Agentline without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves authentication codes from email, which is a read operation with no direct data modification. However, severity is elevated to 'high' because captured 2FA codes could be abused by an agent to bypass security controls, authenticate as other users, or compromise accounts—a significant blast radius despite being technically read-only.
From the tool's definition Tool name 'capture_email_code' suggests retrieving verification codes from email; server description confirms this capability to 'capture 2FA codes'.
Attacks that exploit this kind of access
capture_email_code. It is categorised as a Read tool in the Agentline MCP Server, which means it retrieves data without modifying state.
Register the Agentline MCP server in PolicyLayer and add a rule for capture_email_code: 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 Agentline. Nothing to install.
capture_email_code 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 capture_email_code 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 capture_email_code. 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.
capture_email_code is provided by the Agentline MCP server (jgottlieb84/agentline-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 →