AI agents call browser_storage_get_indexeddb to retrieve information from Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves IndexedDB data from a browser context. It performs no creation, modification, deletion, or execution of arbitrary code—only inspection and retrieval of existing stored data. While IndexedDB may contain sensitive information, the tool itself is passive and read-only.
From the tool's definition Tool description states 'Inspect IndexedDB databases and their data' - inspect is a read-only operation that retrieves data without modification.
Attacks that exploit this kind of access
Inspect IndexedDB databases and their data (see browser_docs). It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for browser_storage_get_indexeddb: 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 Browser. Nothing to install.
browser_storage_get_indexeddb 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 browser_storage_get_indexeddb 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 browser_storage_get_indexeddb. 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.
browser_storage_get_indexeddb is provided by the Browser MCP server (ricardodeazambuja/browser-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 →