invalidate_queries · Tanstack Start Devtools MCP

WHAT IT DOES

What invalidate_queries does on Tanstack Start Devtools

AI agents invoke invalidate_queries to trigger actions in Tanstack Start Devtools. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why invalidate_queries needs a policy

Invalidating queries causes the browser app to mark all cached data as stale and trigger refetches, which is an external operation with side effects on the running application's state. It doesn't delete data permanently, but it does actively trigger network requests and state changes in the browser app, making it Execute rather than Write or Read.

From the tool's definition 'invalidate all React Query queries' — triggers an external operation in the connected browser app that forces all queries to be refetched

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

invalidate_queries Rate-limited

invalidate_queries stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "invalidate_queries": {
      "limits": [
        {
          "counter": "invalidate_queries_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tanstack Start Devtools, so you can run agents against it safely.

FAQ

Questions about invalidate_queries

What does the invalidate_queries tool do? +

Asks the connected browser app to invalidate all React Query queries. It is categorised as a Execute tool in the Tanstack Start Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invalidate_queries? +

Register the Tanstack Start Devtools MCP server in PolicyLayer and add a rule for invalidate_queries: 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.

What risk level is invalidate_queries? +

invalidate_queries is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit invalidate_queries? +

Yes. Add a rate_limit block to the invalidate_queries 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.

How do I block invalidate_queries completely? +

Set action: deny in the PolicyLayer policy for invalidate_queries. 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.

What MCP server provides invalidate_queries? +

invalidate_queries 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.