browser_storage_state
AI agents call browser_storage_state to retrieve information from Playwright MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Browser storage state typically retrieves the current storage state of the browser including cookies, localStorage, and sessionStorage. This is a Read operation, but carries high severity because storage state often contains sensitive authentication tokens, session data, and personal information that could be exploited if accessed by a malicious actor. Empty description reduces confidence in this classification.
From the tool's definition Tool name 'browser_storage_state' suggests retrieving browser storage state (localStorage, sessionStorage, cookies, etc.). Description is empty, lowering confidence.
Attacks that exploit this kind of access
browser_storage_state. It is categorised as a Read tool in the Playwright MCP MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_storage_state: 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 Playwright MCP. Nothing to install.
browser_storage_state 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 browser_storage_state 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 browser_storage_state. 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.
browser_storage_state is provided by the Playwright MCP server (roshan571/playwright-mcp2). 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 →