Find elements by text description
AI agents call ira_find 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 locates elements in the browser DOM based on text matching. It performs information retrieval only—no data is modified, deleted, executed, or financially impacted. While it's part of a browser automation suite with more dangerous capabilities (like ira_click, ira_drag, ira_console), this specific tool itself is a harmless read operation.
From the tool's definition Tool name 'ira_find' and description 'Find elements by text description' indicate a query/search operation that retrieves information about DOM elements without modifying state or executing actions.
Attacks that exploit this kind of access
Find elements by text description. 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_find: 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_find 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_find 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_find. 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_find 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 →