Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-jvm-diagnostics Analyze this thread dump for deadlocks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that gives AI assistants the ability to analyze JVM thread dumps and GC logs. It detects deadlocks, identifies lock contention hotspots, analyzes garbage collection pressure, and recommends JVM tuning parameters.
JVM diagnostic MCP servers exist (TDA, jfr-mcp, Arthas) — but they're all Java-based, requiring a JVM runtime just to diagnose JVM problems. This tool runs on Node.js via npx — no JVM, no Docker, no SSH.
It analyzes offline artifacts (thread dumps, GC logs, heap histograms) rather than requiring a running JVM. Paste a thread dump or GC log and get instant analysis.
Related MCP server: JProfiler
6 MCP tools for comprehensive JVM diagnostics
Thread dump analysis — deadlock detection, contention hotspots, thread state breakdown
GC log analysis — pause statistics, heap trends, memory leak detection
Heap histogram analysis — memory leak candidates, classloader leaks, finalization issues
JFR summary — Java Flight Recorder file analysis
Unified diagnosis — cross-correlates thread and GC data
Supports G1, ZGC, Parallel, Serial, and Shenandoah GC formats
No external dependencies — works on local text input, no API keys needed
Generate exportable diagnostic reports (HTML + PDF) with a Pro license key.
Full JVM thread dump analysis report with actionable recommendations
PDF export for sharing with your team
Priority support
$9.00/month — Get Pro License
Pro license key activates the generate_report MCP tool in mcp-jvm-diagnostics.
npx mcp-jvm-diagnosticsOr install globally:
npm install -g mcp-jvm-diagnosticsAdd to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"jvm-diagnostics": {
"command": "npx",
"args": ["-y", "mcp-jvm-diagnostics"]
}
}
}No environment variables needed — this tool works on text input you provide.
Try these prompts in Claude (paste your JVM output):
"Analyze this thread dump: [paste jstack output]" — Detects deadlocks, contention hotspots, and thread state breakdown
"Analyze this GC log: [paste GC log]" — Shows pause statistics, heap trends, and tuning recommendations
"Compare these heap histograms to find memory leaks: BEFORE: [paste] AFTER: [paste]" — Identifies growing classes, classloader leaks, and finalizer issues
analyze_thread_dumpParse a JVM thread dump and analyze thread states, detect deadlocks, and identify lock contention.
Parameters:
thread_dump — The full thread dump text (from jstack <pid>, kill -3, or VisualVM)
Example prompt: "Analyze this thread dump and tell me if there are any deadlocks"
analyze_gc_logParse a GC log and analyze garbage collection patterns, pause times, and memory pressure.
Parameters:
gc_log — The GC log text (from -Xlog:gc* or -verbose:gc)
Example prompt: "Analyze this GC log and tell me if there are any performance issues"
analyze_heap_histoParse jmap -histo output and detect memory leak candidates, object creation hotspots, and classloader leaks.
Parameters:
histo — The jmap -histo output text (from jmap -histo <pid> or jmap -histo:live <pid>)
Example prompt: "Analyze this heap histogram and tell me if there are any memory leak candidates"
diagnose_jvmUnified JVM diagnosis combining thread dump and GC log analysis for comprehensive root cause analysis.
Parameters:
thread_dump (optional) — Thread dump text
gc_log (optional) — GC log text
Example prompt: "I have both a thread dump and GC log from the same time — diagnose what's wrong"
compare_heap_histosCompare two jmap -histo snapshots taken at different times to detect memory growth patterns and leak candidates.
Parameters:
before — The first (earlier) jmap -histo output
after — The second (later) jmap -histo output
Example prompt: "Compare these two heap histograms and tell me what's growing"
Detects:
Classes with growing instance/byte counts (leak candidates)
New classes that appeared between snapshots
Classes that disappeared (GC'd or unloaded)
Overall heap growth rate
Classloader leaks and finalizer queue growth
# Using jstack
jstack <pid> > thread-dump.txt
# Using kill signal (Linux/Mac)
kill -3 <pid>
# Using jcmd
jcmd <pid> Thread.print > thread-dump.txtAdd these JVM flags to your application:
# Java 9+ (unified logging)
-Xlog:gc*:file=gc.log:time,level,tags
# Java 8
-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:gc.logClone the repo
npm install
npm run build
npm test
Text input only: Thread dumps, GC logs, and heap histograms must be provided as text. The server cannot attach to a running JVM or capture data automatically.
Java 9+ GC logs: The GC log parser is optimized for unified logging format (-Xlog:gc*). Legacy -verbose:gc format (Java 8) has basic support but may miss some events.
Shenandoah GC: Limited support. G1, ZGC, Parallel, and Serial are fully supported.
Virtual threads (Java 21+): Thread dump parser handles virtual threads but analysis recommendations are tuned for platform threads.
Heap histo comparison: Requires standard jmap -histo or jcmd GC.class_histogram format. Custom formats or truncated output may not parse correctly.
Deadlock detection: Detects monitor-based deadlocks. ReentrantLock deadlocks may not be detected if lock addresses are not visible in the thread dump.
No historical analysis: Each analysis is a point-in-time snapshot. For trend analysis, compare multiple snapshots manually.
HotSpot/OpenJDK only: Parser targets HotSpot/OpenJDK thread dump format. GraalVM native-image or Eclipse OpenJ9 dumps may parse incompletely.
Classloader leak detection: Heap analysis flags growing ClassLoader instances but cannot definitively prove a leak without memory profiler data.
mcp-db-analyzer — PostgreSQL/MySQL/SQLite schema analysis
mcp-spring-boot-actuator — Spring Boot health, metrics, and bean analysis
mcp-redis-diagnostics — Redis memory, slowlog, and client diagnostics
mcp-migration-advisor — Flyway/Liquibase migration risk analysis
MIT
End-of-life: 2026-05-10.
This MCP server is no longer maintained or distributed. The Corporation
has pivoted to Apify marketplace actors. See
irrationalways on Apify and
irrcorp/bzp-poland-tenders for current Corporation work.
The npm package has been unpublished. The repository is archived for historical reference only.
Parse a JVM GC log and analyze garbage collection patterns, pause times, allocation rates, and memory pressure. Supports G1, ZGC, Parallel, Serial, and Shenandoah GC formats.
| Name | Required | Description | Default |
|---|---|---|---|
| gc_log | Yes | The GC log text (from -Xlog:gc* or -verbose:gc) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes what the tool does but does not disclose whether it is read-only (likely safe), any authentication requirements, rate limits, or side effects. For a log analysis tool, read-only nature should be stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff. First sentence front-loads the action and outputs. Second sentence adds supportive detail. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a JVM GC log analysis tool with no output schema, the description should hint at the return format (e.g., structured data vs. summary). It covers inputs and analysis scope adequately but falls short of full completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter described as 'The GC log text'. The description adds value by listing supported GC formats, which helps the agent provide appropriate input. This goes beyond the schema's simple description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verb 'Parse' and resource 'JVM GC log', and lists analysis areas (pause times, allocation rates, memory pressure) and supported formats (G1, ZGC, Parallel, Serial, Shenandoah), clearly distinguishing from sibling tools like analyze_jfr or analyze_thread_dump.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context is clear: this tool is for analyzing JVM GC logs. It doesn't explicitly state when not to use it or mention alternatives, but the sibling tool names and description imply specialization.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse jmap -histo output and detect memory leak candidates, object creation hotspots, classloader leaks, and heap composition issues.
| Name | Required | Description | Default |
|---|---|---|---|
| histo | Yes | The jmap -histo output text. Use `jmap -histo:live <pid>` for leak detection — the :live flag forces a full GC first so only reachable objects appear, giving the clearest signal for leaks. Use `jmap -histo <pid>` (without :live) for a cheaper snapshot that includes unreachable objects not yet collected. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so description carries the burden. It discloses that the tool parses and detects various heap issues, implying read-only analysis. It does not explicitly state non-destructiveness or side effects, but the analysis nature suggests no modification. The parameter description adds behavioral context about input options.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 22 words that efficiently conveys the tool's capabilities without redundancy. No wasted words; every part adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the single parameter with full schema description and no output schema, the description adequately covers the tool's function. It tells what input is expected and what analysis is performed. The parameter description is detailed. No gaps remain for the intended complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter described in the schema. The description adds significant value beyond the schema by explaining how to obtain the proper input (with :live for leak detection, without for cheaper snapshot), enabling the agent to produce correct input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: parse jmap -histo output and detect memory leak candidates, object creation hotspots, classloader leaks, and heap composition issues. It specifies the input type and the analysis outputs, distinguishing it from siblings like analyze_jfr (JFR data) or analyze_thread_dump (thread dumps).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives like compare_heap_histos for comparison. The parameter description provides guidance on using :live vs without, but overall usage context is only implied. No direct 'when to use' or 'when not to use' advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse JDK Flight Recorder summary output and analyze event distribution, detect performance hotspots, GC pressure, lock contention, I/O patterns, and excessive allocations. Input must be the text printed to stdout by jfr summary <recording.jfr> — not the binary .jfr file itself.
| Name | Required | Description | Default |
|---|---|---|---|
| jfr_summary | Yes | The stdout text from running `jfr summary <recording.jfr>` (a text table of event types, counts, and sizes — not the binary .jfr file) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It discloses the input constraint (text vs binary) but does not mention behavioral traits like idempotency, side effects, or error handling. The tool appears to be a read-only analyzer, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first lists capabilities, the second provides a critical input constraint. Every word is necessary, no fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one parameter and no output schema or annotations, the description adequately explains what the tool does and what input it expects. It could mention the return format or error behavior for completeness, but for a simple analysis tool, it is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter. The description adds value beyond the schema by clarifying that the input must be the stdout text from `jfr summary`, not the binary file. This prevents common misuse.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool parses JDK Flight Recorder summary output and analyzes various performance aspects (event distribution, hotspots, GC, lock contention, I/O, allocations). The verb 'parse' and 'analyze' with specific resource 'JFR summary output' makes the purpose unambiguous and distinct from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly specifies the input format: 'text printed to stdout by `jfr summary <recording.jfr>`' and warns against providing the binary .jfr file. This is a clear usage guideline. However, it does not explicitly state when not to use this tool or mention alternative tools for different data types.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse a JVM thread dump (jstack output) and analyze thread states, detect deadlocks, identify lock contention hotspots, and find thread starvation patterns. Handles both platform threads and virtual threads (Java 21+). Note: deadlock detection covers synchronized monitor locks only — java.util.concurrent.locks.ReentrantLock and other j.u.c lock types do not expose their waiters in thread dump lock info and will not be detected.
| Name | Required | Description | Default |
|---|---|---|---|
| thread_dump | Yes | The full thread dump text (from jstack, kill -3, or VisualVM) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses a significant limitation: deadlock detection only covers synchronized monitor locks, not j.u.c locks. This transparency about behavioral constraints is valuable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each earning its place: first sentence states purpose, second mentions virtual thread support, third discloses limitation. No unnecessary words, well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about the output format or what the tool returns. Without an output schema, an AI agent would not know what to expect. The description covers input well but omits output details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'thread_dump' has 100% schema coverage. The description adds context by naming common sources (jstack, kill -3, VisualVM) and specifying the accepted format, going beyond the schema's generic description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verbs 'Parse... and analyze' and clearly identifies the resource as a 'JVM thread dump (jstack output)'. It lists specific analysis goals (deadlocks, lock contention, thread starvation) which distinguishes it from sibling tools like analyze_jfr or analyze_gc_log.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for thread dump analysis scenarios but does not explicitly state when to use this tool over alternatives. However, the clear purpose differentiates it from siblings, providing implicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compare two jmap -histo snapshots taken at different times to detect memory growth patterns, leak candidates, and new allocations. Captures what is growing between snapshots.
| Name | Required | Description | Default |
|---|---|---|---|
| after | Yes | The SECOND (later) jmap -histo output. Capture after reproducing the suspected leak or after running under load. Allow at least 5-10 minutes between snapshots — short gaps may not accumulate enough growth to distinguish real leaks from normal allocation churn. Use the same `jmap -histo:live` flag as the before snapshot for a fair comparison. | |
| before | Yes | The FIRST (earlier) jmap -histo output. Capture from a stable baseline — before the suspected leak window or after application startup has settled. Use `jmap -histo:live <pid>` to force a GC before capturing, ensuring unreachable objects are excluded and the snapshot reflects true live objects. |
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 does not explicitly state behavioral traits (e.g., read-only, destructive, permissions needed). However, the parameter descriptions offer good context on proper timing and flags, which partly compensates. Overall, some behavioral insight is present but it is not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, highly concise, and front-loaded with the core purpose. Every word adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and moderate complexity, the description fails to explain the return format or what the comparison output looks like (e.g., delta report). It does not fully prepare an agent for what to expect after invocation, which is a significant gap for a comparison tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The tool description itself ('Compare two jmap -histo snapshots...') adds minimal parameter meaning beyond what the schema already provides. The schema descriptions are quite detailed, so the tool description does not need to compensate; a 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('compare') and resource ('jmap -histo snapshots'), and clearly states the goal ('detect memory growth patterns, leak candidates, and new allocations'). It distinguishes from sibling tools like 'analyze_heap_histo' which likely handles single histograms.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for comparing two snapshots, but does not explicitly state when to use it over alternatives (e.g., 'analyze_heap_histo' for single snapshot analysis). The parameter descriptions provide some usage hints (e.g., gap timing), but the main description lacks clear guidance on when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Unified JVM diagnosis combining thread dump and GC log analysis with cross-correlation. Detects deadlocks, lock contention, GC pressure, and GC-induced cascading thread blocks. When both inputs are provided from the same time window, cross-correlates high GC overhead with contention and flags long GC pauses causing thread starvation. Either input can be omitted for single-source analysis.
| Name | Required | Description | Default |
|---|---|---|---|
| gc_log | No | GC log text (from -Xlog:gc* for Java 9+, or -verbose:gc for Java 8). Provide the portion covering the time window when the thread dump was taken — trim the log to the symptom window if it is large. Logs from a different time period produce spurious correlations. | |
| thread_dump | No | Thread dump text (from jstack, kill -3, or VisualVM). Capture during active symptoms for meaningful cross-correlation — a dump from a healthy period will not correlate with GC pressure visible in the log. |
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 discloses that cross-correlation requires aligned time windows and warns about spurious correlations with mismatched logs. However, it does not describe what the tool returns (e.g., format of diagnosis output) or any side effects, which is a gap for a diagnostic tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of three sentences with clear, front-loaded purpose. Each sentence adds distinct information: purpose, cross-correlation behavior, and single-source option. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex diagnostic tool with no output schema, the description should explain what the tool returns or how results are presented. It lacks this, making it incomplete despite good input guidance. The sibling tools may provide output examples, but this tool's description alone is insufficient for an agent to fully understand the output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions. The description adds significant value beyond the schema by explaining how to use each parameter (e.g., trim GC log to symptom window, capture thread dump during active symptoms) and the consequences of misalignment (spurious correlations). This greatly aids correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a 'Unified JVM diagnosis combining thread dump and GC log analysis with cross-correlation' and lists specific detections (deadlocks, lock contention, GC pressure, GC-induced cascading thread blocks). This distinguishes it from sibling tools like analyze_thread_dump and analyze_gc_log.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (when both inputs are from same time window for cross-correlation) and that either input can be omitted for single-source analysis. However, it does not explicitly suggest alternatives like analyze_thread_dump for thread-only analysis or analyze_gc_log for GC-only analysis, leaving the agent to infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate an exportable diagnostic report (HTML + PDF) from JVM diagnostic data. Requires a valid Pro license key.
| Name | Required | Description | Default |
|---|---|---|---|
| license_key | Yes | A valid MCP JVM Diagnostics Pro license key | |
| thread_dump | Yes | The full thread dump text to analyze and export |
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 discloses the license requirement and output formats, but does not mention behavioral traits such as whether the tool is read-only, requires specific permissions, or has any side effects. As a report generator, it is likely safe, but more disclosure is expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main purpose and output, followed by the key requirement. Every word adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with two parameters and no output schema, the description covers the purpose, output format, and a critical prerequisite. It lacks details about error handling or return values, but is fairly complete given the simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes both parameters with 100% coverage, so the description adds little new meaning. It reinforces the license key requirement but does not elaborate on the thread_dump parameter beyond what is in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates an exportable report (HTML+PDF) from JVM diagnostic data. It uses a specific verb and resource, and the purpose is distinct from sibling tools that analyze specific diagnostic data types, though it does not explicitly differentiate itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions a prerequisite (valid Pro license key), which provides some guidance. However, it does not specify when to use this tool versus alternatives like analyze_thread_dump or diagnose_jvm, leaving usage implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.14analyze_gc_loganalyze_heap_histoanalyze_jfranalyze_thread_dumpcompare_heap_histosdiagnose_jvmgenerate_reportEach tool targets a distinct JVM diagnostic source or operation (JFR, thread dumps, GC logs, heap histograms, comparison, reporting, unified diagnosis), with no functional overlap.
All tools follow a consistent verb_noun pattern in snake_case (e.g., analyze_jfr, generate_report, diagnose_jvm), making the toolset predictable and easy to navigate.
With 7 tools, the server covers the major diagnostic areas (JFR, thread dumps, GC logs, heap histograms, plus comparison and unified analysis) without being bloated or sparse.
The tool surface covers the core diagnostic workflows, but lacks explicit CPU profiling or memory leak tools beyond heap histograms; still, the set is largely complete for general JVM diagnostics.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Ship better Java with your coding agent.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
The Polar Signals MCP server enables AI assistants to connect directly with performance profiling data, allowing users to analyze application performance through natural language queries. Key capabilities include querying CPU performance and memory usage, exploring profiling metadata like profile types and labels, and providing AI-driven code optimization suggestions directly within development environments like Claude Code or Cursor.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Dmitriusan/mcp-jvm-diagnostics'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
