Returns next train arrival for one or more stations. Will return an empty set of results when no predictions are available if a station is closed.\ Some stations have two platforms, like Metro Center, which requires passing in both station codes. For trains with no passengers, the DestinationName...
AI agents call get-wmata-station-info to retrieve information from Subspace Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about train arrivals at DC Metro stations. It performs a read-only operation with no ability to modify, delete, or execute external actions. The data returned is informational only. Even if misused by an agent, the worst outcome would be retrieving irrelevant transit information, which poses minimal risk.
From the tool's definition Tool name 'get-wmata-station-info' and description 'Returns next train arrival' indicates retrieval of real-time transit data with no modification or side effects.
Attacks that exploit this kind of access
Returns next train arrival for one or more stations. Will return an empty set of results when no predictions are available if a station is closed.\ Some stations have two platforms, like Metro Center, which requires passing in both station codes. For trains with no passengers, the DestinationName will be. It is categorised as a Read tool in the Subspace Api MCP Server, which means it retrieves data without modifying state.
Register the Subspace Api MCP server in PolicyLayer and add a rule for get-wmata-station-info: 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 Subspace Api. Nothing to install.
get-wmata-station-info 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-wmata-station-info 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-wmata-station-info. 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-wmata-station-info is provided by the Subspace Api MCP server (subtype-space/subspace-api). 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 →