Perfetto

Turn natural language into powerful Perfetto trace analysis

A Model Context Protocol (MCP) server that transforms natural-language prompts into focused Perfetto analyses. Quickly explain jank, diagnose ANRs, spot CPU hot threads, uncover lock contention, and find memory leaks – all without writing SQL.

- Natural Language → SQL: Ask questions in plain English, get precise Perfetto queries
- ANR Detection: Automatically identify and analyze Application Not Responding events
- Performance Analysis: CPU profiling, frame jank detection, memory leak detection
- Thread Contention: Find synchronization bottlenecks and lock contention
- Binder Profiling: Analyze IPC performance and slow system interactions

- Python 3.13+(macOS/Homebrew):

brew install python@3.13

Or add to~/.cursor/mcp.json(global) or.cursor/mcp.json(project):

{ "mcpServers": { "perfetto-mcp": { "command": "uvx", "args": ["perfetto-mcp"] } } }

Run this command. SeeClaude Code MCP docsfor more info.

# Add to user scope claude mcp add perfetto-mcp --scope user -- uvx perfetto-mcp

{ "mcpServers": { "perfetto-mcp": { "command": "uvx", "args": ["perfetto-mcp"] } } }

or add to.vscode/mcp.json(project) or run "MCP: Add Server" command:

{ "mcpServers": { "perfetto-mcp": { "command": "uvx", "args": ["perfetto-mcp"] } } }

Enable in GitHub Copilot Chat's Agent mode.

[mcp_servers.perfetto-mcp] command = "uvx" args = ["perfetto-mcp"]

Optional: Use a Localtrace_processor_shellBinary

If your network environment blocks downloads, setPERFETTO_MCP_TRACE_PROCESSOR_BIN_PATHto an absolute path of a localtrace_processor_shellbinary.

When this env var is set,perfetto-mcpuses that binary directly. When it is not set, defaultperfettoPython behavior is unchanged.

{ "mcpServers": { "perfetto-mcp": { "command": "uvx", "args": ["perfetto-mcp"], "env": { "PERFETTO_MCP_TRACE_PROCESSOR_BIN_PATH": "D:/tools/perfetto/trace_processor_shell.exe" } } } }

[mcp_servers.perfetto-mcp] command = "uvx" args = ["perfetto-mcp"] [mcp_servers.perfetto-mcp.env] PERFETTO_MCP_TRACE_PROCESSOR_BIN_PATH = "D:/tools/perfetto/trace_processor_shell.exe"

cd perfetto-mcp-server uv sync uv run mcp dev src/perfetto_mcp/dev.py

{ "mcpServers": { "perfetto-mcp-local": { "command": "uv", "args": [ "--directory", "/path/to/git/repo/perfetto-mcp", "run", "-m", "perfetto_mcp" ], "env": { "PYTHONPATH": "src" } } } }

pip3 install perfetto-mcp python3 -m perfetto_mcp

In the perfetto trace, I see that the FragmentManager is taking 438ms to execute. Can you figure out why it's taking so long?

Be explicit about the trace and process, prefix your prompt with:

"Use perfetto trace/absolute/path/to/trace.perfetto-tracefor processcom.example.app"

Many tools support additional filtering (but let your LLM handle that):

- time_range:{start_ms: 10000, end_ms: 25000}
- Tool-specific thresholds:min_block_ms,jank_threshold_ms,limit

Note: Helpful if the recorded trace contains ANR

- Summary: High-level findings
- Details: Tool-specific results
- Metadata: Execution context and any fallbacks used

- Trace Processor Python API- Perfetto's Python interface
- Perfetto SQL Syntax- SQL reference for custom queries

Apache 2.0 License. SeeLICENSEfor details.

An agentic toolkit to control, debug, and profile iOS and Android apps.