Skip to main content
Glama
maschiojv

ThreadMine MCP Server

by maschiojv
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

ThreadMine MCP Server

ThreadMine is a Java thread dump analyzer with AI — detects deadlocks, CPU spikes, pool exhaustion and virtual thread pinning. Free online, no signup.

Official MCP server for ThreadMine. Paste a JVM thread dump into your AI assistant — Claude Code, Claude Desktop or Cursor — and get back the detected problems, a health score and a link to the full interactive report, without leaving the chat.

Tools

Tool

What it does

Quota

analyze_thread_dump

Uploads a thread dump (inline text or file path) and returns detected problems, health score (0-100) and the report link

Consumes 1 analysis from your daily quota

get_analysis

Fetches a previous analysis by id

Free (read-only)

Related MCP server: mcp-dotnet-diagnostics

Setup

  1. Create a free account at threadmine.dev.

  2. Create an API key: Settings → API Keys in the web app.

  3. Add the server to your assistant:

Claude Code

claude mcp add threadmine -e THREADMINE_API_KEY=tf_live_xxx -- npx -y @threadmine/mcp

Claude Desktop / Cursor (claude_desktop_config.json / .cursor/mcp.json)

{
  "mcpServers": {
    "threadmine": {
      "command": "npx",
      "args": ["-y", "@threadmine/mcp"],
      "env": { "THREADMINE_API_KEY": "tf_live_xxx" }
    }
  }
}

Usage

Ask your assistant things like:

  • "Analyze this thread dump: <paste>"

  • "Run the dump at /tmp/threaddump.txt through ThreadMine"

  • "What did analysis <id> find? Any deadlocks?"

Notes

  • Analyses run in the workspace the API key belongs to and count against that workspace's plan quota (the Free plan includes a daily quota — pricing).

  • THREADMINE_API_URL can override the API endpoint (self-hosted / staging).

  • Requires Node.js ≥ 20.

License

MIT

Available Tools

2 tools
analyze_thread_dumpA

Analyze a JVM thread dump with ThreadMine. Detects deadlocks, CPU spikes, thread pool exhaustion, thread leaks and virtual thread pinning. Returns detected problems, a health score (0-100) and a link to the full interactive report. Pass the dump text in "content", or "file_path" for large dumps. Consumes one analysis from the ThreadMine account's daily quota.

ParametersJSON Schema
NameRequiredDescriptionDefault
titleNoOptional title for the analysis
contentNoRaw thread dump text (jstack / jcmd Thread.print / kill -3 output)
file_pathNoAbsolute path to a thread dump file — preferred for large dumps

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, but the description discloses important behavioral traits: it consumes daily quota, returns a health score and link, and detects specific problems. No contradiction with annotations since none exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at three sentences, front-loads the purpose and key behaviors, and every sentence contributes meaningful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explains what is returned (problems, health score, link) and covers quota consumption. All three parameters are addressed, and no critical information is missing for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by stating that file_path is preferred for large dumps, and clarifies that content is raw dump text, going beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it analyzes JVM thread dumps and enumerates specific detections (deadlocks, CPU spikes, etc.), distinguishing it from the sibling tool 'get_analysis' which likely retrieves past results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool (to analyze thread dumps) and provides guidance on passing data via content or file_path for large dumps. It could explicitly mention when not to use it, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_analysisA

Fetch an existing ThreadMine analysis by id (returned by analyze_thread_dump). Read-only: does NOT consume the daily analysis quota.

ParametersJSON Schema
NameRequiredDescriptionDefault
analysis_idYesThe analysis id (UUID)

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It explicitly states the tool is read-only and does not consume a daily quota, covering both safety and resource constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no unnecessary words, efficiently conveying all critical information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), the description covers purpose, parameter origin, behavioral constraints, and quota impact, making it fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes 'analysis_id' as a UUID with 100% coverage. The description adds valuable context by noting it is returned by 'analyze_thread_dump', helping the agent understand where to obtain the parameter value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Fetch' and clearly identifies the resource as 'existing ThreadMine analysis by id', distinguishing it from the sibling 'analyze_thread_dump' by referencing it as the source of the id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies that this tool should be used after 'analyze_thread_dump' to retrieve an analysis by its returned id, providing clear context. It lacks explicit when-not-to-use instructions, but the sibling context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedanalyze_thread_dump
    • First observedget_analysis
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.6/5.0
Disambiguation5/5

The two tools are clearly distinct: one submits a new thread dump for analysis, the other retrieves results by ID. No overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern ('analyze_thread_dump', 'get_analysis'), making them predictable and easy to distinguish.

Tool Count4/5

Two tools is reasonable for a specialized analysis server. It covers the essential create and retrieve operations without unnecessary bloat.

Completeness4/5

The server covers the core workflow (analyze and retrieve results). Missing list or delete functionality are minor gaps but do not break the usage flow.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Perfetto MCP

    antarikshc
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables natural language analysis of Perfetto traces to diagnose Android app performance issues like ANRs, jank, CPU hotspots, memory leaks, and lock contention without writing SQL queries.
    217
    Apache 2.0

  • mcp-dotnet-diagnostics

    aayushmdesai
    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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maschiojv/threadmine-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server