AI agents call suggest_tests to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs analysis and suggestion of test cases based on existing code symbols. This is a read-only operation: it retrieves information about a symbol and generates recommendations without side effects such as creating, modifying, deleting, or executing code. Even though it involves AI-driven analysis, the output is purely advisory (suggestions), not an action that changes state or runs operations.
From the tool's definition Tool description states 'Suggest test cases for a symbol using AI' — a suggestive/analytical operation that reads code symbols and proposes test cases without modifying, deleting, or executing code.
Documented attack patterns abuse exactly the kind of access suggest_tests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for suggest_tests:
{
"version": "1",
"default": "deny",
"tools": {
"suggest_tests": {}
}
}suggest_tests 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.
Suggest test cases for a symbol using AI. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for suggest_tests: 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 Trace. Nothing to install.
suggest_tests 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 suggest_tests 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 suggest_tests. 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.
suggest_tests is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.