通过具体的中文车站名查询其
AI agents call get-station-code-by-names to retrieve information from 12306 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns station code information based on input parameters. It performs a straightforward data retrieval operation without creating, modifying, deleting, or executing any actions. All sibling tools (get-current-date, get-stations-code-in-city, get-train-route-stations, etc.) are also read-only queries.
From the tool's definition Tool name 'get-station-code-by-names' and description indicate a query operation that retrieves station codes based on station names. This is a lookup/retrieval function with no side effects.
Documented attack patterns abuse exactly the kind of access get-station-code-by-names gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 12306, and nothing reaches the server without passing your rules. This is the rule we recommend for get-station-code-by-names:
{
"version": "1",
"default": "deny",
"tools": {
"get-station-code-by-names": {}
}
}get-station-code-by-names 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.
通过具体的中文车站名查询其. It is categorised as a Read tool in the 12306 MCP Server, which means it retrieves data without modifying state.
Register the 12306 MCP server in PolicyLayer and add a rule for get-station-code-by-names: 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 12306. Nothing to install.
get-station-code-by-names 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-station-code-by-names 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-station-code-by-names. 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-station-code-by-names is provided by the 12306 MCP server (joooook/12306-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 12306, 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.
8 12306 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.