AI agents call get_connections to retrieve information from Mcp Swiss without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns information about existing train and bus connections—a pure data lookup with no side effects, no code execution, and no data modification. It belongs in the Read category. Severity is low because misuse would only result in information disclosure of already-public transportation data.
From the tool's definition Tool name 'get_connections' and description 'Get train/bus connections between two Swiss locations' indicate a read-only query operation that retrieves public transportation schedule data without modifying or executing external operations.
Attacks that exploit this kind of access
Get train/bus connections between two Swiss locations. It is categorised as a Read tool in the Mcp Swiss MCP Server, which means it retrieves data without modifying state.
Register the Mcp Swiss MCP server in PolicyLayer and add a rule for get_connections: 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 Mcp Swiss. Nothing to install.
get_connections 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_connections 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_connections. 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_connections is provided by the Mcp Swiss MCP server (mcp-swiss). 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 →