Fetch rolling stock (vehicle) information
AI agents call rolling-stock to retrieve information from Open Data Model Context Protocol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'fetch' and the context of accessing 'public datasets' (per server description) clearly establish this as a read-only data retrieval tool. It retrieves vehicle information without creating, modifying, deleting, or executing any operations. The low severity reflects minimal risk even if misused, as it only exposes public railway vehicle data.
From the tool's definition Tool name 'rolling-stock' and description 'Fetch rolling stock (vehicle) information' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Fetch rolling stock (vehicle) information. It is categorised as a Read tool in the Open Data Model Context Protocol MCP Server, which means it retrieves data without modifying state.
Register the Open Data Model Context Protocol MCP server in PolicyLayer and add a rule for rolling-stock: 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 Open Data Model Context Protocol. Nothing to install.
rolling-stock 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 rolling-stock 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 rolling-stock. 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.
rolling-stock is provided by the Open Data Model Context Protocol MCP server (opendatamcp/opendatamcp). 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 →