AI agents use update_ui_schema to create or update resources in Nocobase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nocobase environment.
This tool creates or modifies data reversibly. It updates UI schema configuration without deleting records or executing arbitrary code. The 'partial update' nature indicates data is changed but not destroyed. Given it affects UI presentation layer, it could have moderate impact if misused to alter application interface, but is reversible and doesn't execute commands, delete data, or move financial resources.
From the tool's definition Tool performs 'Patch an existing UI schema node by UID (partial update)' — a modification operation that changes UI schema data
Attacks that exploit this kind of access
Patch an existing UI schema node by UID (partial update). It is categorised as a Write tool in the Nocobase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nocobase MCP server in PolicyLayer and add a rule for update_ui_schema: 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 Nocobase. Nothing to install.
update_ui_schema 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 update_ui_schema 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 update_ui_schema. 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.
update_ui_schema is provided by the Nocobase MCP server (puguhsudarma/nocobase-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 →