Find circular dependency chains in the import graph (Kosaraju SCC algorithm). Considers only import-typed edges (esm_imports / imports / py_imports / py_reexports); call, reference, member_of, and test_covers edges are NOT walked. Test files (paths matching tests/, /*.test.*, /*.spec.*, /__tests_...
AI agents call get_circular_imports 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.
This tool only retrieves and analyzes structural information from the codebase dependency graph. It has no side effects, does not execute code, modify files, or trigger external operations. The explicit 'Read-only' designation confirms it is purely an analysis/query tool with minimal blast radius if misused by an agent.
From the tool's definition Tool description states 'Read-only' and performs analysis of import graphs using Kosaraju SCC algorithm to detect circular dependencies. Returns JSON data without modifying code or dependencies.
Documented attack patterns abuse exactly the kind of access get_circular_imports 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 get_circular_imports:
{
"version": "1",
"default": "deny",
"tools": {
"get_circular_imports": {}
}
}get_circular_imports 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.
Find circular dependency chains in the import graph (Kosaraju SCC algorithm). Considers only import-typed edges (esm_imports / imports / py_imports / py_reexports); call, reference, member_of, and test_covers edges are NOT walked. Test files (paths matching tests/, /*.test.*, /*.spec.*, /__tests__/) are excluded by default to suppress spurious test↔source cycles — pass include_tests: true to opt in. Use to detect and break dependency cycles. Read-only. Returns JSON: { total_cycles, cycles: [{ files, length }] }. 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 get_circular_imports: 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.
get_circular_imports 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_circular_imports 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_circular_imports. 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_circular_imports 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.