browser_snapshot
AI agents call browser_snapshot 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.
The tool appears to capture or retrieve the current DOM/accessibility state of a browser page, which is a read operation. However, severity is elevated to medium rather than low because: (1) the description is empty, reducing confidence slightly; (2) snapshots of web pages could potentially expose sensitive data depending on what's displayed; (3) in the context of a browser automation tool alongside write/execute…
From the tool's definition Tool name 'browser_snapshot' combined with server description indicating 'accessibility snapshots' suggests the tool retrieves the current state of a web page without modifying it.
Attacks that exploit this kind of access
browser_snapshot. 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_snapshot: 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_snapshot 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_snapshot 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_snapshot. 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_snapshot is provided by the Playwright MCP server (naumana3services-maker/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 →