Inspect a running IntelliJ process through MCP to see CPU activity, thread states, and stack snapshots. Use the captured evidence to triage freezes, blocked threads, or performance symptoms and decide when deeper profiling is needed.
Inspect a running IntelliJ IDE for freezes or blocked threads via MCP.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Use the get_ide_diagnostics MCP tool to answer "what is this IDE doing right now?" from inside a running IntelliJ process.
This skill is for live IDE process evidence only. If the request is to diagnose an arbitrary issue, inspect repository code, analyze build/test output, or debug the MCP server itself, use the relevant debugging, testing, or code-investigation workflow instead.
The diagnostics toolset is hidden unless the IDE was started with:
-Didea.diagnostics.mcp.enabled=true
If get_ide_diagnostics is not available, tell the user the IDE must be restarted with that property. Do not confuse it with MCP server self-diagnostics; the property enables IDE process diagnostics exposed through MCP.
Start with a lightweight CPU sample without the raw dump:
{
"sampleMillis": 1000,
"topThreadCount": 25,
"includeRawDump": false
}
For freezes, blocked threads, or coroutine investigation, request a bounded raw dump:
{
"sampleMillis": 1000,
"topThreadCount": 50,
"includeRawDump": true,
"maxDumpChars": 200000,
"stripCoroutineDump": true
}
For action-specific performance questions, take one sample before or during the action and another while the symptom is visible. Compare topCpuThreads, blockedCountDelta, waitedCountDelta, and threads.stateCounts between samples.
process.processCpuLoad and process.systemCpuLoad are point-in-time process/system CPU load values; -1 means the JVM cannot provide the metric.topCpuThreads[].cpuDeltaNanos ranks threads by CPU consumed during sampleMillis; -1 means thread CPU time is unavailable.topCpuThreads[].state is the JVM Thread.State; RUNNABLE includes Java execution and native calls, including native I/O.topCpuThreads[].isInNative, nativeFrame, and nativeOperationHint help identify native calls, but they are not OS wait-channel data.topCpuThreads[].stackTrace is a short stack snapshot for attribution, not a full profiler call tree.threads.stateCounts is useful for spotting many BLOCKED, WAITING, or TIMED_WAITING threads.rawDump is the IntelliJ thread dump text and may include coroutine dump content when coroutine dumping is enabled in the running IDE.rawDumpTruncated=true means repeat with a larger maxDumpChars or ask for a narrower next step before drawing conclusions from missing tail content.coroutineDumpEnabled=false means the tool cannot provide coroutine dump details beyond ordinary thread stacks.Use this MCP tool for low-overhead triage and evidence gathering. For root-cause CPU attribution, allocation pressure, lock profiling, native wait-state attribution, or long recordings, ask for JFR, async-profiler, or the IDE's standard performance capture workflow.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Implement or update IntelliJ `AnAction` classes and their `plugin.xml` registrations. Keep labels and descriptions in message bundles, configure optional icons, and launch suspending work through the event coroutine scope so synchronous action handling does not freeze the IDE.
Move IntelliJ JPS test modules to Bazel and diagnose failures that occur only under Bazel. The guide helps trace missing dependencies, plugins, test data, and runfiles, then verify the generated target and migrated tests.
Write or review Kotlin and Java code in line with IntelliJ project conventions. The guidance covers language choice, formatting, sealed types, threading annotations, and safe handling of control flow exceptions so changes fit the surrounding codebase.
Create, amend, or rename IntelliJ commits with messages that follow the project’s ticket and label formats. Keep each commit focused, explain the reason and decision in the body when needed, and pass the message safely through the shell or PowerShell.
Compare how Python type checkers interpret a code snippet or file. The script runs selected tools, including ty, pyrefly, basedpyright, mypy, and zuban, then produces a Markdown report with verdicts, timings, and each checker's diagnostic output.
Shape Compose Desktop UI code by keeping composables focused on rendering and placing application decisions in presenters or coordinators. Get guidance on state ownership, effects, reusable component APIs, lazy-list keys, animation, and performance for individual UI changes.