Press the key
AI agents invoke press-key to trigger actions in TgeBrowser 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.
Pressing a key is an interactive browser action that executes input events within the automated browser. It can trigger form submissions, navigation, scripts, or other side effects depending on context. This falls under Execute as it performs external browser operations whose effects depend on arguments (which key is pressed and in what context).
From the tool's definition 'Press the key' — triggers a keyboard input action within a browser automation environment
Attacks that exploit this kind of access
Press the key. It is categorised as a Execute tool in the TgeBrowser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TgeBrowser MCP Server MCP server in PolicyLayer and add a rule for press-key: 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 TgeBrowser MCP Server. Nothing to install.
press-key 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 press-key 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 press-key. 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.
press-key is provided by the TgeBrowser MCP Server MCP server (tuguang2025/tgebrowser-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 →