AI agents call get_city_weather to retrieve information from Doubao MCP Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves weather information for specified cities without modifying, creating, deleting, or executing any operations. It is purely informational and read-only, presenting minimal security risk to users or systems.
From the tool's definition Tool description indicates it 'queries city weather' (查询城市天气) for supported Chinese cities. The verb '查询' (query/retrieve) and the list of cities show this is a data retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_city_weather gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Doubao MCP Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for get_city_weather:
{
"version": "1",
"default": "deny",
"tools": {
"get_city_weather": {}
}
}get_city_weather is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
查询城市天气，支持中文城市：北京/上海/广州/深圳/成都等. It is categorised as a Read tool in the Doubao MCP Agent MCP Server, which means it retrieves data without modifying state.
Register the Doubao MCP Agent MCP server in PolicyLayer and add a rule for get_city_weather: 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 Doubao MCP Agent. Nothing to install.
get_city_weather is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_city_weather 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 get_city_weather. 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.
get_city_weather is provided by the Doubao MCP Agent MCP server (taffy123d/localskill-mcp-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Doubao MCP Agent, 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 Doubao MCP Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.