# benchmark_project Synthetic token efficiency benchmark: compare raw file reads vs trace-mcp compact responses across symbol lookup, file exploration, search, and impact analysis scenarios. Read-only, no side effects. Use to quantify token savings. Returns JSON: { scenarios: [{ name, raw_tokens, compact_tokens, savings_pct }], summary }. Agent View of the PolicyLayer registry record for `benchmark_project`. HTML page: https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/benchmark-project ## Facts - Tool: `benchmark_project` - Server: Trace (`nikolai-vysotskyi/trace-mcp`) — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp.md - Homepage: https://github.com/nikolai-vysotskyi/trace-mcp - Risk category: Read (Low risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Allowed ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "benchmark_project", "arguments": {} } } ``` ## Why benchmark_project is rated Low This tool performs benchmarking analysis by comparing token efficiency metrics across different lookup and search scenarios. It retrieves and compares data to generate performance statistics, with no capability to modify code, execute operations, or cause side effects. The explicit 'read-only' designation confirms it falls under the Read category with low severity risk. From the tool's own definition: "Tool description explicitly states 'Read-only, no side effects' and operations are limited to 'compare raw file reads vs trace-mcp compact responses' and 'Returns JSON' with metrics. No modification, execution, deletion, or financial operations occur." ## Use case AI agents call benchmark_project to retrieve information from Trace without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere. ## Recommended policy (PolicyLayer) Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Trace: ```json { "version": "1", "default": "deny", "tools": { "benchmark_project": {} } } ``` ## Other tools on Trace (190) - `delete_corpus` — Destructive — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/delete-corpus.md - `remove_dead_code` — Destructive — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/remove-dead-code.md - `repair_index` — Destructive — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/repair-index.md - `call_project_tool` — Execute — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/call-project-tool.md - `reindex` — Execute — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/reindex.md - `visualize_graph` — Execute — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/visualize-graph.md - `analyze_perf` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/analyze-perf.md - `assess_change_risk` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/assess-change-risk.md - `audit_config` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/audit-config.md - `check_architecture` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-architecture.md - `check_claudemd_drift` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-claudemd-drift.md - `check_duplication` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-duplication.md - `check_edit_safe` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-edit-safe.md - `check_embedding_drift` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-embedding-drift.md - `check_quality_gates` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-quality-gates.md - `check_rename` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/check-rename.md - `compare_branches` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/compare-branches.md - `detect_antipatterns` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/detect-antipatterns.md - `detect_ast_clones` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/detect-ast-clones.md - `detect_communities` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/detect-communities.md - `detect_drift` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/detect-drift.md - `detect_topic_tunnels` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/detect-topic-tunnels.md - `diff_graph_snapshots` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/diff-graph-snapshots.md - `discover_claude_sessions` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/discover-claude-sessions.md - `discover_hermes_sessions` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/discover-hermes-sessions.md - `embed_repo` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/embed-repo.md - `explain_architecture` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/explain-architecture.md - `explain_symbol` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/explain-symbol.md - `export_decisions` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/export-decisions.md - `export_graph` — Read — https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp/export-graph.md - …and 160 more: https://policylayer.com/tools/nikolai-vysotskyi-trace-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=nikolai-vysotskyi-trace-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/nikolai-vysotskyi-trace-mcp