AI agents call get_item_decisions 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 'get_' prefix conventionally indicates retrieval operations. Despite the empty description, the naming pattern and the sibling tools (which include write operations like 'add_decision', 'delete_decision', 'edit_item', etc.) confirm this is a read operation. Retrieving decisions for an item has no side effects and poses minimal risk if misused by an agent.
From the tool's definition Tool name 'get_item_decisions' with 'get' prefix indicates data retrieval. No description provided, but the verb 'get' combined with context of a kanban board management system suggests querying existing decision records associated with an item without…
Documented attack patterns abuse exactly the kind of access get_item_decisions 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 get_item_decisions:
{
"version": "1",
"default": "deny",
"tools": {
"get_item_decisions": {}
}
}get_item_decisions 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_item_decisions. 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 get_item_decisions: 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.
get_item_decisions 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_item_decisions 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_item_decisions. 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_item_decisions 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.