AI agents use open_dashboard to create or update resources in Osv Ui — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Osv Ui environment.
An AI agent can call open_dashboard faster than any human can review — one bad instruction and it creates or modifies resources in Osv Ui by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Launch the osv-ui visual dashboard in the browser for human review. It is categorised as a Write tool in the Osv Ui MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Osv Ui MCP server in PolicyLayer and add a rule for open_dashboard: 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 Osv Ui. Nothing to install.
open_dashboard 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 open_dashboard 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 open_dashboard. 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.
open_dashboard is provided by the Osv Ui MCP server (toan203/osv-ui). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.