Skip to main content
Glama

sleuths-mcp

A production-troubleshooting MCP server for AI agents. Turns thread dumps, GC logs and heap histograms into deterministic structured diagnostics (deadlocks, hot locks, bottleneck frames), so Cursor / Claude / Copilot pinpoint the problem directly — instead of hallucinating from raw logs.

▶ Live Demo · English · 中文

Install

Requires Node.js 18+. No global install needed — run directly with npx:

npx -y sleuths-mcp

Or install globally:

npm install -g sleuths-mcp

Related MCP server: ThreadMine MCP Server

Setup with your AI client

Add sleuths to your MCP client (Cursor / Claude / Copilot):

{
  "mcpServers": {
    "sleuths": {
      "command": "npx",
      "args": ["-y", "sleuths-mcp"]
    }
  }
}

Then just say: "analyze this thread dump".

Features

  • Deterministic parsing: no LLM hallucination; reproducible and testable

  • Standard MCP protocol: STDIO transport, works with Cursor / Claude / Copilot

  • Zero intrusion: only parses existing diagnostic artifacts; never attaches to your app

  • One-command install: npx -y sleuths-mcp, no Java runtime required

Tools

Tool

Description

Status

analyze_thread_dump

Thread dumps: deadlocks, state distribution, hot locks, top frames

✅ MVP

parse_exception_log

Exception aggregation: group by type, root-cause chain, count

✅ MVP

analyze_gc_log

GC logs: Young/Full counts, avg/max pause, memory trend

✅ MVP

analyze_heap_histo

Heap histogram: top classes by bytes, suspected leaks

✅ MVP

Develop

npm install
npm run build
node dist/index.js

License

MIT

Available Tools

4 tools
analyze_gc_logAnalyze GC LogB

Parse JVM GC logs and return: total GC events, Young/Full counts, average and max pause time, memory trend, and whether Full GC is frequent.

Inputs: logs (required).

analyze_heap_histoAnalyze Heap HistogramA

Parse jmap -histo output: top classes by bytes, total heap, and suspected application-level memory leaks (non-JDK classes taking >5% heap).

Inputs: histo (required).

analyze_thread_dumpAnalyze Thread DumpA

Parse a jstack / jcmd Thread.print thread dump text and return: total thread count, state distribution, deadlocked threads, hot locks, top frames.

Inputs: dump (required).

parse_exception_logParse Exception LogsA

Aggregate raw exception logs: group by exception type, count occurrences, extract root cause (Caused-by chain) and first frame. Returns a structured summary you can use to tell which error dominates and where it originates.

Inputs: logs (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct JVM diagnostic artifact: thread dumps, exception logs, GC logs, and heap histograms. There is no meaningful overlap in purpose, so an agent can select the right tool from the input type alone.

    Naming Consistency5/5

    All names follow a consistent snake_case verb_noun pattern. The verbs alternate between analyze and parse, but both are semantically appropriate and the structure remains highly predictable.

    Tool Count5/5

    Four tools is well-scoped for a focused JVM diagnostics server. Each tool covers a distinct and commonly needed artifact, so none feels redundant or out of place.

    Completeness4/5

    The surface covers the core JVM troubleshooting artifacts: thread dumps, exception aggregation, GC logs, and heap histograms. Minor gaps exist around heap dump analysis and JFR-style profiling, but the main diagnostic workflows are supported.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Live .NET runtime diagnostics for AI assistants. Ask Claude to diagnose memory leaks, GC pressure, LOH fragmentation, and thread starvation in any running .NET process — no code changes required.
      7
      2
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables analysis of JVM thread dumps to detect deadlocks, CPU spikes, pool exhaustion, and virtual thread pinning, returning a health score and interactive report link.
      2
      86 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Lets AI agents diagnose and debug live Java applications by auto-discovering JVMs and attaching Arthas to run diagnostic commands like thread, trace, watch, and ognl.
      5
      MIT