Batch create tags.
AI agents use dida365_create_tags to create or update resources in Dida365 Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dida365 Agent environment.
This tool creates new tags in bulk, which is a reversible write operation. Tags are metadata entities that can be deleted or modified later. There is no code execution, financial impact, or destructive action involved. The blast radius is minimal—creating tags does not affect task data, system integrity, or critical operations; worst case, an agent creates unwanted tags that can be cleaned up.
From the tool's definition Tool name includes 'create' and description states 'Batch create tags' - creates new tag data in the task management system without deletion or execution of external code.
Attacks that exploit this kind of access
Batch create tags. It is categorised as a Write tool in the Dida365 Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dida365 Agent MCP server in PolicyLayer and add a rule for dida365_create_tags: 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 Dida365 Agent. Nothing to install.
dida365_create_tags 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 dida365_create_tags 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 dida365_create_tags. 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.
dida365_create_tags is provided by the Dida365 Agent MCP server (linhai0872/dida365-agent). 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 →