Get the current state of a connected test, including DOM, snapshot, console logs, and available context APIs. The response includes
AI agents call get_current_test_state to retrieve information from Testing without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the state of an active test environment. The language is purely informational—'get', 'includes'—indicating read-only access to test metadata and debugging information. No side effects are described. While it operates in a test context, it does not execute test steps, modify test data, or trigger external operations; it only observes and reports state.
From the tool's definition Tool description states it 'Get[s] the current state' and 'includes' information retrieval (DOM, snapshot, console logs, context APIs) without indicating any modification, deletion, or execution of operations.
Documented attack patterns abuse exactly the kind of access get_current_test_state gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Testing, and nothing reaches the server without passing your rules. This is the rule we recommend for get_current_test_state:
{
"version": "1",
"default": "deny",
"tools": {
"get_current_test_state": {}
}
}get_current_test_state 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.
Get the current state of a connected test, including DOM, snapshot, console logs, and available context APIs. The response includes. It is categorised as a Read tool in the Testing MCP Server, which means it retrieves data without modifying state.
Register the Testing MCP server in PolicyLayer and add a rule for get_current_test_state: 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 Testing. Nothing to install.
get_current_test_state 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_test_state 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_test_state. 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_test_state is provided by the Testing MCP server (mcpland/testing-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Testing, 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.
5 Testing tools catalogued and risk-classified — across an index of 43,000+ MCP servers.