AI agents use create_openspec_project to create or update resources in Trae-OpenSpec MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trae-OpenSpec MCP environment.
This tool creates new project artifacts and structures, which constitutes data modification. However, it is reversible (projects can be deleted or modified later), so it is Write rather than Destructive. The blast radius is medium because an AI agent could create numerous unwanted projects consuming resources, but the action is not irreversible.
From the tool's definition Tool description indicates it 'automatically creates OpenSpec projects' based on requirements. The verb 'create' and context of 'creation and management' in server description show this tool generates and establishes new project structures.
Documented attack patterns abuse exactly the kind of access create_openspec_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trae-OpenSpec MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_openspec_project:
{
"version": "1",
"default": "deny",
"tools": {
"create_openspec_project": {
"limits": [
{
"counter": "create_openspec_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_openspec_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.
基于需求描述自动创建OpenSpec项目. It is categorised as a Write tool in the Trae-OpenSpec MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trae-OpenSpec MCP server in PolicyLayer and add a rule for create_openspec_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 Trae-OpenSpec MCP. Nothing to install.
create_openspec_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_openspec_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_openspec_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_openspec_project is provided by the Trae-OpenSpec MCP server (leon30083/trae-openspec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Trae-OpenSpec MCP, 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.
3 Trae-OpenSpec MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.