断开与浏览器的连接
AI agents use disconnect_browser to create or update resources in MCP Browser Logger — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Browser Logger environment.
This tool modifies the state of the connection to the browser by terminating it, making it a Write operation rather than Read (which would only query state). It is not Destructive because the disconnection is reversible—logs and data remain intact. It is not Execute because it does not run code or trigger external operations with argument-dependent effects.
From the tool's definition Tool name 'disconnect_browser' indicates it disconnects/terminates an active browser connection. The description '断开与浏览器的连接' (Chinese: 'disconnect from the browser') confirms this is a state-modifying operation that closes a connection, which is reversible…
Attacks that exploit this kind of access
断开与浏览器的连接. It is categorised as a Write tool in the MCP Browser Logger MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Browser Logger MCP server in PolicyLayer and add a rule for disconnect_browser: 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 MCP Browser Logger. Nothing to install.
disconnect_browser is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the disconnect_browser 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 disconnect_browser. 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.
disconnect_browser is provided by the MCP Browser Logger MCP server (tao-lionel/mcp-browser-logger). 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 →