AI agents use move_tasks to create or update resources in Tick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tick environment.
Moving tasks changes their organizational state but does not create, delete, or execute arbitrary operations. This is a Write-category action: reversible data modification. Severity is medium because bulk task movements could disrupt workflow organization, but effects are recoverable. Confidence is slightly reduced due to empty description, though the tool name and server context provide reasonable inference.
From the tool's definition Tool name 'move_tasks' indicates modification of task state/position. Description is empty, limiting direct evidence, but sibling tools like 'batch_update_tasks', 'batch_delete_tasks', and 'complete_task' establish this server manages TickTick task mutations.
Attacks that exploit this kind of access
move_tasks. It is categorised as a Write tool in the Tick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tick MCP server in PolicyLayer and add a rule for move_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 Tick. Nothing to install.
move_tasks 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 move_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 move_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.
move_tasks is provided by the Tick MCP server (kpihx/tick-mcp). 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 →