AI agents call check_disruptions to retrieve information from SNCF API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve real-time or current disruption data from the SNCF railway system, consistent with other query-based tools on the server. No side effects, state changes, or irreversible actions are implied. The lack of description slightly reduces confidence, but the naming convention and context are sufficient to classify this as a Read operation with low severity risk.
From the tool's definition Tool name 'check_disruptions' with empty description suggests querying/retrieving disruption information from SNCF's railway network. The verb 'check' indicates a retrieval operation without modification.
Documented attack patterns abuse exactly the kind of access check_disruptions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SNCF API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for check_disruptions:
{
"version": "1",
"default": "deny",
"tools": {
"check_disruptions": {}
}
}check_disruptions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
check_disruptions. It is categorised as a Read tool in the SNCF API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SNCF API MCP Server MCP server in PolicyLayer and add a rule for check_disruptions: 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 SNCF API MCP Server. Nothing to install.
check_disruptions 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 check_disruptions 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 check_disruptions. 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.
check_disruptions is provided by the SNCF API MCP Server MCP server (kryzo/mcp-sncf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SNCF API MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 SNCF API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.