View cookies, localStorage, sessionStorage
AI agents call ira_storage 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 stored browser data (cookies, localStorage, sessionStorage) without creating, modifying, or deleting it. While this is classified as Read, the severity is elevated to medium because the data accessed may include sensitive information such as authentication tokens, session IDs, or other personally identifiable information that could be misused if an AI agent accesses storage from websites the user…
From the tool's definition Tool description states: 'View cookies, localStorage, sessionStorage'. The verb 'View' and the storage types listed are all read-only operations that retrieve data without modification.
Attacks that exploit this kind of access
View cookies, localStorage, sessionStorage. 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_storage: 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_storage 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_storage 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_storage. 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_storage 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 →