Find Type-2 AST clones across the codebase: functions/methods with identical structure after normalizing identifiers and literals. Unlike check_duplication (name/signature similarity — Type-1-ish), this parses each function body with tree-sitter, replaces identifiers and literals with a placehold...
AI agents call detect_ast_clones 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 is a pure analysis tool that retrieves and reports structural patterns in source code. It performs static analysis (AST parsing and hashing) to identify code clones but produces no side effects, creates no persistent changes, and executes no external operations. The explicit 'Read-only' designation confirms it fits the Read category.
From the tool's definition Tool description explicitly states 'Read-only' and 'Find Type-2 AST clones across the codebase' — it parses and analyzes code structure without modifying, deleting, or executing anything. Returns JSON results for inspection only.
Documented attack patterns abuse exactly the kind of access detect_ast_clones 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 detect_ast_clones:
{
"version": "1",
"default": "deny",
"tools": {
"detect_ast_clones": {}
}
}detect_ast_clones 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 Type-2 AST clones across the codebase: functions/methods with identical structure after normalizing identifiers and literals. Unlike check_duplication (name/signature similarity — Type-1-ish), this parses each function body with tree-sitter, replaces identifiers and literals with a placeholder, and hashes the AST subtree. Reports groups of structurally identical symbols — prime candidates for DRY refactoring or extracting a shared helper. Supported languages: TypeScript, JavaScript, Python, Ruby, Go, Java, Rust, PHP, C, C++, C#, Swift, Kotlin, Scala, Elixir. Read-only. Returns JSON: { groups: [{ hash, size, loc, symbols: [{ symbol_id, name, file, line_start, line_end }] }], total_groups, total_duplicated_symbols, files_scanned, symbols_scanned }. 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 detect_ast_clones: 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.
detect_ast_clones 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 detect_ast_clones 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 detect_ast_clones. 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.
detect_ast_clones 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.