管理云托管服务，按开发顺序支持：初始化项目（可从模板开始，模板列表可通过 queryCloudRun 查询）、下载服务代码、本地运行（仅函数型服务）、部署代码、删除服务。部署可配置CPU、内存、实例数、访问类型等参数。删除操作需要确认，建议设置force=true。
AI agents call manageCloudRun to permanently remove resources in CloudBase MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool manages cloud-hosted services with operations spanning initialization, deployment, and deletion. The presence of an irreversible delete-service operation with a force=true flag makes it Destructive. Deleting a cloud service is irreversible and has a critical blast radius — it could take down live applications and destroy all associated resources.
From the tool's definition 删除服务 (delete service), 删除操作需要确认，建议设置force=true (delete operation requires confirmation, recommended to set force=true)
Documented attack patterns abuse exactly the kind of access manageCloudRun gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CloudBase MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for manageCloudRun:
{
"version": "1",
"default": "deny",
"hide": [
"manageCloudRun"
]
}manageCloudRun disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
管理云托管服务，按开发顺序支持：初始化项目（可从模板开始，模板列表可通过 queryCloudRun 查询）、下载服务代码、本地运行（仅函数型服务）、部署代码、删除服务。部署可配置CPU、内存、实例数、访问类型等参数。删除操作需要确认，建议设置force=true。. It is categorised as a Destructive tool in the CloudBase MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CloudBase MCP server in PolicyLayer and add a rule for manageCloudRun: 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 CloudBase MCP. Nothing to install.
manageCloudRun is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manageCloudRun 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 manageCloudRun. 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.
manageCloudRun is provided by the CloudBase MCP server (tencentcloudbase/cloudbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 CloudBase MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 CloudBase MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.