last_train_home
AI agents call last_train_home to retrieve information from Swiss Rail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about the last available train for a given route, consistent with journey planning queries on a public transport API. It has no side effects, does not modify data, and poses minimal risk. Classification as Read with low severity is appropriate for informational queries on public transport systems.
From the tool's definition Tool name 'last_train_home' and context as a Swiss public transport MCP server suggest this queries train schedule data. Sibling tools (get_connections, get_stationboard, get_disruptions) are all Read operations.
Attacks that exploit this kind of access
last_train_home. It is categorised as a Read tool in the Swiss Rail MCP Server, which means it retrieves data without modifying state.
Register the Swiss Rail MCP server in PolicyLayer and add a rule for last_train_home: 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 Swiss Rail. Nothing to install.
last_train_home 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 last_train_home 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 last_train_home. 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.
last_train_home is provided by the Swiss Rail MCP server (kintscher/swiss-rail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →