Open email in browser
AI agents invoke open-email to trigger actions in Gmail MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Opening an email in a browser is an external operation that launches a browser and navigates to a resource. This is not a pure read (no data is returned to the agent) but rather an Execute action that triggers an external application. Misuse could expose email content in unintended contexts or trigger browser-based vulnerabilities, warranting medium severity.
From the tool's definition 'Open email in browser' — triggers an external browser action to open/display content
Attacks that exploit this kind of access
Open email in browser. It is categorised as a Execute tool in the Gmail MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for open-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 Gmail MCP Server. Nothing to install.
open-email is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open-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 open-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.
open-email is provided by the Gmail MCP Server MCP server (jmonsellier/gmail-mcp-server). 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 →