AI agents use create-project to create or update resources in Dida — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dida environment.
This tool creates a new project in the TickTick/Dida365 task management system. Creating a project is a Write operation because it modifies state by adding new data. It is reversible since projects can be deleted. The severity is low because creating a project has minimal blast radius—it does not delete data, execute arbitrary code, move money, or cause system-wide harm.
From the tool's definition Tool name 'create-project' and description 'Create a new project' indicate a data creation operation that is reversible (projects can be deleted via the sibling tool 'delete-project').
Documented attack patterns abuse exactly the kind of access create-project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dida, and nothing reaches the server without passing your rules. This is the rule we recommend for create-project:
{
"version": "1",
"default": "deny",
"tools": {
"create-project": {
"limits": [
{
"counter": "create-project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create-project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new project. It is categorised as a Write tool in the Dida MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dida MCP server in PolicyLayer and add a rule for create-project: 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 Dida. Nothing to install.
create-project 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 create-project 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 create-project. 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.
create-project is provided by the Dida MCP server (zhongwencool/dida-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dida, 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.
18 Dida tools catalogued and risk-classified — across an index of 43,000+ MCP servers.