AI agents call get_engaged_tasks to retrieve information from Ticktick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the sibling tool patterns and naming convention, this tool retrieves task data (likely tasks marked as 'engaged' or 'in progress') without side effects. Although the description is empty, the naming evidence is strong. Confidence is reduced from 0.9 to 0.85 due to missing explicit description, but the contextual pattern is reliable.
From the tool's definition Tool name 'get_engaged_tasks' follows the naming pattern of sibling read-only tools like 'get_all_tasks', 'get_next_tasks', and 'get_overdue_tasks', all of which retrieve task data without modification.
Documented attack patterns abuse exactly the kind of access get_engaged_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ticktick, and nothing reaches the server without passing your rules. This is the rule we recommend for get_engaged_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"get_engaged_tasks": {}
}
}get_engaged_tasks 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_engaged_tasks. It is categorised as a Read tool in the Ticktick MCP Server, which means it retrieves data without modifying state.
Register the Ticktick MCP server in PolicyLayer and add a rule for get_engaged_tasks: 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 Ticktick. Nothing to install.
get_engaged_tasks 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_engaged_tasks 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_engaged_tasks. 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_engaged_tasks is provided by the Ticktick MCP server (jacepark12/ticktick-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ticktick, 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.
22 Ticktick tools catalogued and risk-classified — across an index of 43,000+ MCP servers.