AI agents call list_children to retrieve information from Kanban without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to list child items within a hierarchical structure (likely sub-tasks, sub-epics, or related items in a kanban board). This is a retrieval operation with no side effects on the data. While the empty description reduces certainty, the conventional semantics of 'list' in API design strongly suggest a Read operation. Severity is low because listing data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'list_children' indicates retrieval of hierarchical data without modification. The 'list' prefix conventionally denotes a Read operation that queries and returns data. No description provided, but the naming pattern aligns with data retrieval.
Documented attack patterns abuse exactly the kind of access list_children gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kanban, and nothing reaches the server without passing your rules. This is the rule we recommend for list_children:
{
"version": "1",
"default": "deny",
"tools": {
"list_children": {}
}
}list_children 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.
list_children. It is categorised as a Read tool in the Kanban MCP Server, which means it retrieves data without modifying state.
Register the Kanban MCP server in PolicyLayer and add a rule for list_children: 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 Kanban. Nothing to install.
list_children 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 list_children 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 list_children. 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.
list_children is provided by the Kanban MCP server (multidimensionalcats/kanban-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kanban, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
45 Kanban tools catalogued and risk-classified — across an index of 43,000+ MCP servers.