Routes via OpenRouteService (votre clé)
AI agents call get_travel_time to retrieve information from Concierge Voyage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries OpenRouteService to retrieve route and travel time data. This is a read-only operation with no side effects — it fetches information without creating, modifying, or deleting any data. Severity is low as misuse would at worst return incorrect routing information. Confidence is slightly reduced because the description is minimal and in mixed language, leaving some ambiguity about full capabilities.
From the tool's definition 'Routes via OpenRouteService' — the tool calculates travel routes/times by querying an external routing API
Attacks that exploit this kind of access
Routes via OpenRouteService (votre clé). It is categorised as a Read tool in the Concierge Voyage MCP MCP Server, which means it retrieves data without modifying state.
Register the Concierge Voyage MCP server in PolicyLayer and add a rule for get_travel_time: 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 Concierge Voyage MCP. Nothing to install.
get_travel_time 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_travel_time 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_travel_time. 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_travel_time is provided by the Concierge Voyage MCP server (wassima-azzouzi/concierge-voyage-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 →