// MCP TOOL REFERENCE

TESTING TOOLS

5 tools from the Testing MCP Server, categorised by risk level.

// ALL 5 TESTING TOOLS

READ 3 tools

Read get_current_test_state Get the current state of a connected test, including DOM, snapshot, console logs, and available context API... Read get_generated_code Get all generated code blocks from a test file Read list_active_tests List all currently connected test processes

DESTRUCTIVE 1 tools

Destructive finalize_test Finalize the test by removing connect() call and optionally cleaning up markers

EXECUTE 1 tools

Execute execute_test_step Execute code directly in the connected test client and get back the updated DOM state and console logs. IMP...

// FAQ

How many tools does the Testing MCP server have? +

The Testing MCP server exposes 5 tools across 3 categories: Read, Destructive, Execute.

How do I enforce policies on Testing tools? +

Route the Testing server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Testing tools fall into? +

Testing tools are categorised as Read (3), Destructive (1), Execute (1). Each category has a recommended default policy.

Enforce policy on every Testing tool call.

Start from Testing, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.