{"id":"antarikshc-perfetto-mcp","name":"perfetto-mcp","homepage":null,"repo_url":"https://github.com/antarikshc/perfetto-mcp","category":"ai-ml","subcategories":[],"tags":["mcp","perfetto","android-tracing","observability","profiling","debugging","perfetto-sql","agent-tools"],"what_it_does":"perfetto-mcp is a local Model Context Protocol (MCP) server that turns natural-language prompts into Perfetto trace analyses (including generating PerfettoSQL) for tasks like jank/ANR detection, CPU hotspot analysis, lock contention, Binder transaction profiling, and memory leak signals.","use_cases":["Analyze Android Perfetto traces via natural-language requests","Diagnose jank (missing frame deadlines) and summarize frame performance","Detect and investigate ANR events and likely root causes","Identify CPU hot threads/scheduling hotspots","Find lock contention / thread synchronization bottlenecks","Profile Binder IPC latency and group slow transactions","Detect suspected memory leak patterns and heap dominators"],"not_for":["Using as a hosted SaaS/API service (it appears intended to run locally as an MCP stdio server)","Production workflows requiring guaranteed, reproducible analysis without validation of generated SQL","Scenarios where you cannot provide local trace files (requires trace_path as input)"],"best_when":"You have one or more Perfetto trace files locally and want an agent to orchestrate analysis by calling MCP tools that return structured JSON results.","avoid_when":"You need authentication/authorization controls, network-access APIs, or strict compliance claims without additional vetting; also avoid untrusted trace content ingestion in sensitive environments without sandboxing.","alternatives":["Direct use of Perfetto Trace Processor (Python API) and Perfetto SQL","Other MCP servers or agent toolchains specialized for Perfetto/trace analysis","Custom scripts/notebooks using perfetto trace processor APIs"],"af_score":56.2,"security_score":22.8,"reliability_score":26.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:44:38.923064+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["No explicit auth described (local stdio MCP server)"],"oauth":false,"scopes":false,"notes":"README describes running the MCP server locally (e.g., uvx/uv) and provides required tool parameters (trace_path, process_name). No user authentication mechanism is documented, suggesting it runs without auth in a local developer environment."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information; appears to be an open-source package executed locally."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":56.2,"security_score":22.8,"reliability_score":26.2,"mcp_server_quality":72.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":0.0,"tls_enforcement":0.0,"auth_strength":10.0,"scope_granularity":0.0,"dependency_hygiene":55.0,"secret_handling":60.0,"security_notes":"No network interface or TLS/auth is described; the server runs locally via stdio. This reduces remote attack surface, but increases risk from any tools that may read local trace files (sensitive data). No explicit guidance on sandboxing, trace file validation, logging of sensitive data, or handling of malicious trace contents is provided. Dependencies include mcp[cli], perfetto, protobuf<5, which may warrant dependency/CVE review before use in sensitive environments.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":40.0,"error_recovery":20.0,"idempotency_support":"false","idempotency_notes":"Likely deterministic for a given trace_path and prompt, but idempotency guarantees are not stated; tooling appears to run analysis jobs rather than change remote state.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Tool inputs require absolute trace_path and a process_name; incorrect paths/process names may yield empty or failed analyses.","Generated SQL/tool behavior depends on the trace containing the relevant events (e.g., ANRs); prompts should constrain time ranges and expectations.","Because it is a local MCP stdio server, agents need to launch it correctly (command/args) per client (Cursor/Claude/Copilot/etc.)."]}}