AI agents use test_code to create or update resources in Claude Code — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code environment.
The tool generates (creates) test code, which is a Write operation — it produces new artifacts. It does not execute code, delete anything, or move money. Severity is medium because generated test code could contain unexpected logic, but the primary action is content creation.
From the tool's definition Generates tests for the given code
Documented attack patterns abuse exactly the kind of access test_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code, and nothing reaches the server without passing your rules. This is the rule we recommend for test_code:
{
"version": "1",
"default": "deny",
"tools": {
"test_code": {
"limits": [
{
"counter": "test_code_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}test_code stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generates tests for the given code. It is categorised as a Write tool in the Claude Code MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Code MCP server in PolicyLayer and add a rule for test_code: 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 Claude Code. Nothing to install.
test_code is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the test_code 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 test_code. 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.
test_code is provided by the Claude Code MCP server (kunihiros/claude-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code, 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.
7 Claude Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.