get_accessibility_tree
AI agents call get_accessibility_tree to retrieve information from Selenium MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves structural information about the page (accessibility tree) without modifying state, executing code, or triggering side effects. Despite empty description, the name and context of other read-only tools on this Selenium server strongly indicate this is a query/fetch operation.
From the tool's definition Tool name 'get_accessibility_tree' indicates retrieval of accessibility/DOM tree structure from the current webpage; consistent with sibling tools like 'get_page_text', 'get_page_title', and 'get_interactive_elements' which are all read-only data retrieval…
Attacks that exploit this kind of access
get_accessibility_tree. It is categorised as a Read tool in the Selenium MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP Server 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 Selenium MCP Server. 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 Selenium MCP Server MCP server (nayakprashant/selenium-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 →