AI agents call onui_get_annotations to retrieve information from onUI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves annotation data from a specific page without modifying, deleting, or executing any operations. It is a pure read operation with minimal risk—even if misused by an AI agent, it only exposes existing annotation metadata without causing destructive changes or financial impact.
From the tool's definition Tool name 'onui_get_annotations' and description 'Get annotations for a specific page URL' indicate a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access onui_get_annotations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and onUI, and nothing reaches the server without passing your rules. This is the rule we recommend for onui_get_annotations:
{
"version": "1",
"default": "deny",
"tools": {
"onui_get_annotations": {}
}
}onui_get_annotations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get annotations for a specific page URL. It is categorised as a Read tool in the onUI MCP Server, which means it retrieves data without modifying state.
Register the onUI MCP server in PolicyLayer and add a rule for onui_get_annotations: 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 onUI. Nothing to install.
onui_get_annotations 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 onui_get_annotations 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 onui_get_annotations. 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.
onui_get_annotations is provided by the onUI MCP server (onllm-dev/onui). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 onUI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 onUI tools catalogued and risk-classified — across an index of 42,500+ MCP servers.