Get the accessibility tree of the page
AI agents call get_accessibility_tree to retrieve information from Browser MCP Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The accessibility tree is a read-only data structure representing page semantics and UI hierarchy. Retrieving it has no side effects—it does not execute JavaScript, modify the DOM, delete data, or move resources. It is purely informational, analogous to inspecting page structure.
From the tool's definition Tool name and description indicate retrieval-only operation: 'Get the accessibility tree of the page' is a query that returns structural data (accessibility tree) without modifying state, executing code, or triggering side effects.
Attacks that exploit this kind of access
Get the accessibility tree of the page. It is categorised as a Read tool in the Browser MCP Bridge MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP Bridge MCP server in PolicyLayer and add a rule for get_accessibility_tree: 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 Browser MCP Bridge. Nothing to install.
get_accessibility_tree 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 get_accessibility_tree 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 get_accessibility_tree. 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.
get_accessibility_tree is provided by the Browser MCP Bridge MCP server (robhicks/browser-mcp-bridge). 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 →