Get accessibility tree
AI agents call ira_read_page to retrieve information from IRA-RESEARCHER without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the accessibility tree (DOM structure and text content) from a webpage, which is a read-only query operation. It has no capability to modify, delete, or execute actions. While it operates in a browser automation context with other tools capable of clicking and executing scripts, this specific tool only reads and returns data about the page structure.
From the tool's definition Tool name is 'ira_read_page' and description states 'Get accessibility tree' — both indicate retrieval of page structure/content data with no modification capability.
Attacks that exploit this kind of access
Get accessibility tree. It is categorised as a Read tool in the IRA-RESEARCHER MCP Server, which means it retrieves data without modifying state.
Register the IRA-RESEARCHER MCP server in PolicyLayer and add a rule for ira_read_page: 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 IRA-RESEARCHER. Nothing to install.
ira_read_page 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 ira_read_page 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 ira_read_page. 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.
ira_read_page is provided by the IRA-RESEARCHER MCP server (neuralnexustech/ira-researcher). 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 →