AI agents call get_flow_model_by_parent to retrieve information from Nocobase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves flow model information based on parent ID and subKey parameters. The retrieval operation has no side effects, does not modify data, and does not trigger external actions or code execution. It is a simple query/fetch operation typical of navigation and data inspection within a data hierarchy.
From the tool's definition Tool description states 'Get a flowPage block/model by its parent ID and subKey' — the verb 'Get' combined with 'for navigating' indicates read-only retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Get a flowPage block/model by its parent ID and subKey. Useful for navigating the flowPage block tree. It is categorised as a Read tool in the Nocobase MCP Server, which means it retrieves data without modifying state.
Register the Nocobase MCP server in PolicyLayer and add a rule for get_flow_model_by_parent: 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.
get_flow_model_by_parent 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 get_flow_model_by_parent 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 get_flow_model_by_parent. 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.
get_flow_model_by_parent 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 →