sbb_search_stations
AI agents call sbb_search_stations to retrieve information from SBB Open Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves station data with no apparent side effects. It fits the Read category (search, list, get, fetch). The empty description slightly reduces confidence, but the naming pattern matches other Read tools on the server (sbb_list_datasets, sbb_get_* pattern). No data modification, deletion, code execution, or financial operations are indicated.
From the tool's definition Tool name 'sbb_search_stations' indicates a search/query operation. The server description states it enables AI models to 'query' SBB open data including 'station details' without side effects.
Attacks that exploit this kind of access
sbb_search_stations. It is categorised as a Read tool in the SBB Open Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SBB Open Data MCP Server MCP server in PolicyLayer and add a rule for sbb_search_stations: 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 SBB Open Data MCP Server. Nothing to install.
sbb_search_stations 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 sbb_search_stations 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 sbb_search_stations. 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.
sbb_search_stations is provided by the SBB Open Data MCP Server MCP server (malkreide/sbb-opendata-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 →