transit_departures
Get live public-transport departures with real-time delays for a stop. Sourced from GTFS-RT/HVV/VGN. Unlike the static stop list (get_city_resource(slug, resource='transit')), this returns minute-fresh departures including delay for ONE stop. A stop_id is required: fetch the city's transit stops ...
This record as markdown: /tools/dev-infranode-infranode/transit-departures.md
What transit_departures does on InfraNode
AI agents call transit_departures to retrieve information from InfraNode without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
slug | string | Yes | City identifier, e.g. 'berlin' or 'hamburg'. Resolved leniently: the German name with or without umlauts, any casing, a common English exonym or short form also |
stop_id | object | — | Required stop ID to fetch departures for. Discover a city's stop IDs with get_city_resource(slug, resource='transit') first (each stop carries its id). Format: |
Parameters from the server's own tool schema.
Why transit_departures is rated Low
Retrieves real-time transit data without modifying or deleting any system state.
From the tool's definition Get live public-transport departures, read-only, no side effects
Attacks that exploit this kind of access
The rule that runs transit_departures safely
PolicyLayer is an MCP gateway: it sits between your AI agents and InfraNode, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For transit_departures, this is the rule to start with:
transit_departures is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect InfraNode, apply this rule, and every transit_departures call is checked against it from then on.
Questions about transit_departures
Get live public-transport departures with real-time delays for a stop. Sourced from GTFS-RT/HVV/VGN. Unlike the static stop list (get_city_resource(slug, resource='transit')), this returns minute-fresh departures including delay for ONE stop. A stop_id is required: fetch the city's transit stops first to discover valid stop IDs, then pass one here. Read-only. It is categorised as a Read tool in the InfraNode MCP Server, which means it retrieves data without modifying state.
transit_departures accepts 2 parameters: slug, stop_id. Required: slug. The full parameter table on this page comes from the server's own tool schema.
Register the InfraNode MCP server in PolicyLayer and add a rule for transit_departures: 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 InfraNode. Nothing to install.
transit_departures 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 transit_departures 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 transit_departures. 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.
transit_departures is provided by the InfraNode MCP server (https://mcp.infranode.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on InfraNode, and thousands of servers like it.
This server
Across the catalogue