Get page state with interactive elements
AI agents call ira_get_state 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 and reads page state information, which is a non-destructive, passive observation capability. While the server provides browser automation with significant capabilities (including Execute-class tools like ira_click, ira_console, ira_drag), this specific tool only fetches state without triggering side effects.
From the tool's definition Tool name 'ira_get_state' combined with description 'Get page state with interactive elements' indicates a retrieval operation that queries the current state of a web page. No modification, deletion, execution, or financial action is performed.
Attacks that exploit this kind of access
Get page state with interactive elements. 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_get_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 IRA-RESEARCHER. Nothing to install.
ira_get_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 ira_get_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 ira_get_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.
ira_get_state 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 →