AI agents use browser_set_local_storage to create or update resources in Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp environment.
This tool modifies browser localStorage by setting key-value pairs. While the changes are reversible (keys can be overwritten or deleted), the tool enables an agent to persistently alter client-side state for a specific origin, potentially affecting application behavior, authentication tokens, or user preferences.
From the tool's definition Tool "Set a localStorage key to a JSON-serializable value for a specific origin" - the term 'Set' combined with 'key to value' indicates data modification. localStorage is a client-side persistence mechanism that stores data reversibly.
Attacks that exploit this kind of access
Set a localStorage key to a JSON-serializable value for a specific origin inside an existing browser session. It is categorised as a Write tool in the Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP server in PolicyLayer and add a rule for browser_set_local_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 Mcp. Nothing to install.
browser_set_local_storage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_set_local_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 browser_set_local_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.
browser_set_local_storage is provided by the MCP server (victormyschik/mcp). 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 →