Returns the latest route snapshot reported by the TanStack Devtools panel.
AI agents call get_current_route to retrieve information from Tanstack Start Devtools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves the current route state from the TanStack Devtools panel. It performs no modifications, deletions, or external operations—it simply returns existing data. The blast radius of misuse is minimal since reading route state cannot damage systems or data.
From the tool's definition Tool name 'get_current_route' and description 'Returns the latest route snapshot' indicate a read-only retrieval of state information with no side effects.
Attacks that exploit this kind of access
Returns the latest route snapshot reported by the TanStack Devtools panel. It is categorised as a Read tool in the Tanstack Start Devtools MCP Server, which means it retrieves data without modifying state.
Register the Tanstack Start Devtools MCP server in PolicyLayer and add a rule for get_current_route: 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 Tanstack Start Devtools. Nothing to install.
get_current_route 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_current_route 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_current_route. 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_current_route is provided by the Tanstack Start Devtools MCP server (mantrakp04/tanstack-start-dev-tool-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 →