// SCAN REPORT

onUI

8 tools. 4 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

4 can modify or destroy data

4 read-only

8 tools total

Community server · catalogue entry verified 11/06/2026

How to control onUI ↓

TOOL MAP

Read (4) Write / Execute (2) Destructive / Financial (2)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High onui_clear_page_annotations This tool irreversibly removes all annotations associated with a page in one operation. Destructive · High onui_delete_annotation This tool permanently removes annotations without a stated undo mechanism. Write · Medium onui_bulk_update_annotation_metadata This tool creates or modifies annotation metadata in a reversible manner. Write · Medium onui_update_annotation_metadata This is a Write operation because it creates or modifies data reversibly—updating annotation metadata is a non-destructive change that can be undone or corrected.

4 of onUI's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL ONUI

PolicyLayer is an MCP gateway — it sits between your AI agents and onUI, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "onui_clear_page_annotations": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "onui_bulk_update_annotation_metadata": {
    "limits": [
      {
        "counter": "onui_bulk_update_annotation_metadata_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "onui_get_annotations": {
    "limits": [
      {
        "counter": "onui_get_annotations_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register onUI — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ONUI →

Free to start. No card required.

ALL 8 ONUI TOOLS

DESTRUCTIVE 2 tools

Destructive onui_clear_page_annotations Delete all annotations for a specific page URL. Destructive onui_delete_annotation Delete a single annotation by id.

WRITE 2 tools

Write onui_bulk_update_annotation_metadata Bulk update metadata for multiple annotations. Write onui_update_annotation_metadata Update metadata for a single annotation (status/intent/severity/comment).

READ 4 tools

Read onui_get_annotations Get annotations for a specific page URL. Read onui_get_report Generate annotation report in compact/standard/detailed/forensic format. Read onui_list_pages List pages that have onUI annotations in the local store. Read onui_search_annotations Search annotations across the local store with optional filters.

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the onUI MCP server? +

Yes. The onUI server exposes 2 destructive tools including onui_clear_page_annotations, onui_delete_annotation. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through onUI? +

The onUI server has 2 write tools including onui_bulk_update_annotation_metadata, onui_update_annotation_metadata. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach onUI.

How many tools does the onUI MCP server expose? +

8 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on onUI? +

Register the onUI MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every onUI tool call.

Deterministic rules across all 8 onUI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ONUI →

Free to start. No card required.

8 onUI tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

onUI

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL ONUI

// ALL 8 ONUI TOOLS

// RELATED SERVERS

// FAQ