perfsage-jmeter-mcp
The server is a self-healing JMeter MCP that enables LLM agents to perform end-to-end performance testing. It can provision and heal the JMeter runtime (Java, JMeter, plugins, with Docker fallback), import traffic from HAR/OpenAPI/Postman, auto-correlate dynamic values, generate and edit JMX plans, execute load tests with guardrails, discover capacity limits, analyze results at p95/p99, evaluate SLOs, integrate Kubernetes RCA, and compile verdict-led reports.
Environment Management: Diagnose and automatically heal the JMeter environment; ensure Java 21, JMeter 5.6.3, and plugins are installed, with Docker fallback.
Traffic Import & Auto-Correlation: Import traffic recordings from HAR files, OpenAPI specs, or Postman collections; auto-detect format and filter static noise. Automatically correlate dynamic tokens, cookies, and session IDs into JMeter variables.
JMX Plan Generation & Editing: Build JMeter 5.6.3 test plans from correlated flows with configurable workload profiles (fixed, ramp, stress, burst). Perform structured edits on existing plans, including workload strategies, HTTP methods, headers, bodies, and JSR223 scripting.
Controlled Test Execution & Workload Discovery: Execute plans with guardrails (p95 ceiling, error rate thresholds, timeouts) and optional Docker execution. Adaptive concurrency stepping discovers the application’s throughput knee point.
Results Analysis & SLO Gating: Summarize JTL outputs into p95/p99 latencies and bottleneck findings. Gate results against an SLO properties file for pass/fail compliance.
Kubernetes RCA Integration: Correlate test windows with SignalPilot server-side root cause analysis.
Unified Verdict Reporting: Compile Markdown, HTML, and JSON reports with a verdict (PASS/WARN/FAIL) led by p95/p99 metrics, optionally including SLO and RCA data.
Provides tools for automating JMeter performance testing, including environment setup, traffic import, correlation, test execution, workload discovery, and report generation.
Provides integration with Kubernetes to correlate performance test results with cluster metrics for root cause analysis.
Enables importing Postman collections to generate JMeter performance test flows.
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., "@perfsage-jmeter-mcpSet up the environment, import login_flow.har, and give me a capacity recommendation."
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.
🎯 What you get
Stop wrestling with Java paths, broken plugins, and hand-written extractors.
Point Cursor / Claude at this MCP server and ask for a performance test. It will:
Heal Java + Apache JMeter 5.6.3 + plugins under
~/.perfsage(Docker fallback if needed)Import HAR / OpenAPI / Postman traffic
Auto-correlate tokens, cookies, and IDs into JMeter variables
Discover the throughput knee when you don’t know the workload
Report a PASS / WARN / FAIL led by p95 + p99 (never averages alone)
Analysis, not dashboards. Every run ends in a decision.
Related MCP server: JMeter MCP Server (TypeScript Edition)
⚡ 60-second setup
Requires Python 3.10+. Prefer uv (macOS system python3 is often 3.9; uv-managed Pythons also block bare pip via PEP 668).
# try it (no install)
uvx perfsage-jmeter-mcp --version
uvx perfsage-jmeter-mcp# install as a user tool (recommended)
uv tool install perfsage-jmeter-mcp
perfsage-jmeter-mcp --version# or inside a project venv
uv venv --python 3.12
source .venv/bin/activate # Windows: .venv\Scripts\activate
uv pip install perfsage-jmeter-mcpDo not run
python3.12 -m pip install …against a uv-managed interpreter — you’ll getexternally-managed-environment. Useuv tool install/uv pip install/ a venv instead. Apple’s/usr/bin/python3(3.9) cannot see this package at all (requires-python >=3.10).
🔌 Connect Cursor / Claude Desktop
Drop this into your MCP config (examples/cursor-mcp.json):
{
"mcpServers": {
"perfsage-jmeter": {
"command": "uvx",
"args": ["perfsage-jmeter-mcp"]
}
}
}Then say:
“Set up the performance environment, then import
login_flow.harand give me a capacity recommendation.”
That’s the whole onboarding.
Fixture note:
tests/recorder/fixtures/login_flow.hartargetsshop.perfsage.test, which is offline. Use it to demo correlation / JMX generation only — not liverun_testsmoke. For runnable demos, import a HAR against a real host (for example JSONPlaceholder or your own staging URL).
✨ Why teams reach for this
Pain today | With PerfSage JMeter MCP |
❌ “Wrong Java / missing JMeter / plugin chaos” | ✅ |
❌ Manual regex correlation for every token | ✅ |
❌ Guessing thread counts | ✅ |
❌ Average latency gates that lie | ✅ Reports always include p95 + p99 + SLO verdict |
❌ Client metrics disconnected from K8s | ✅ Optional SignalPilot RCA + Reveal charts |
🔁 How it works
Step | Tool | Outcome |
1️⃣ |
| Ready runtime (native or Docker) |
2️⃣ |
| Clean application Flow (static noise filtered) |
3️⃣ |
| Replayable JMeter 5.6.3 plan |
4️⃣ |
| Workload / structure tweaks (burst, loops, JSR223, …) |
5️⃣ |
| Guarded execution + capacity profile |
6️⃣ |
| Markdown + HTML + JSON, verdict first |
💬 Example session
You: Set up the performance environment.
Agent: ensure_environment → ready=true, Java 21 + JMeter 5.6.3 under ~/.perfsage
You: Import tests/recorder/fixtures/login_flow.har (correlation demo; host is offline) and correlate it.
Agent: import_traffic → 4 app requests
correlate_flow → csrf_token, token, cart_id, SESSION (cookie-managed)
You: Generate a fixed plan at 20 threads / 120s, then run a 5-minute burst inside 20 minutes.
Agent: generate_jmx → ${__P(perfsage.threads,20)} / ${__P(perfsage.duration,120)}
edit_jmx → set_workload burst (Ultimate Thread Group)
run_test / discover_workload → guarded execution + capacity
You: Compile the report with examples/slo.properties.
Agent: compile_report → PASS/WARN/FAIL leading with p95 + p99
artifacts → ~/.perfsage/runs/<id>/report/🧰 Tools
Tool | What it does |
🩺 | Diagnose + heal Java / JMeter / plugins / Docker |
🔍 | Read-only readiness report |
📥 | HAR / OpenAPI / Postman → Flow |
🔗 | Dynamic values → variables + extractors |
📝 | Correlated Flow → JMeter 5.6.3 plan |
✏️ | Structured ops on an existing plan (new file by default) |
🚀 | Execute with always-on guardrails |
📈 | Adaptive knee-point discovery |
📊 | JTL → metrics, bottlenecks, p95/p99 |
✅ | Gate against |
☸️ | Merge Kubernetes RCA for the test window |
📦 | Unified Markdown + HTML + JSON |
Full schemas & sample payloads: docs/TOOLS.md
🛡️ Environment gate (runs first)
Every JMeter-touching tool calls ensure_environment first:
Condition | Action |
Java missing / outside 17–21 | Download Temurin JDK 21 into |
JMeter missing / < 5.6.3 | Download Apache JMeter 5.6.3 + verify ASF SHA-512 |
Plugins missing | Install |
Host can’t be provisioned | Fall back to Docker ( |
Neither works | Structured failure: attempted · failed · values |
🔒 Nothing writes outside ~/.perfsage (or your working directory). No JAVA_HOME mutations. No package-manager side effects.
🧩 Ecosystem
Project | Role |
JTL analysis + chart pack | |
SLO gate format + Backend Listener | |
Kubernetes RCA for the test window | |
Brand home · Field Notes · tools |
🛠️ Development
uv run --python 3.12 --extra dev pytest
uv run --python 3.12 --extra dev ruff check .
uv run --python 3.12 --extra dev mypy perfsage_jmeter_mcpReal JMeter e2e: tests/test_end_to_end.py (e2e marker).
Architecture notes: docs/ARCHITECTURE.md
📄 License
MIT
Apache JMeter is a trademark of the Apache Software Foundation. This project is an independent tool and is not affiliated with or endorsed by the ASF.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseBqualityFmaintenanceA Model Context Protocol server that allows AI assistants to execute and manage JMeter performance tests through natural language commands.670
- Alicense-qualityDmaintenanceEnables AI assistants to programmatically create, execute, and analyze Apache JMeter performance tests. It supports automated bottleneck detection, report generation, and distributed testing management through natural language.MIT
- Flicense-qualityCmaintenanceIntegrates Apache JMeter with AI assistants to run and manage load tests through natural language. It enables users to execute test plans, parse results, inspect test structures, and compare performance metrics across different runs.

BlazeMeter MCP Serverofficial
Alicense-qualityBmaintenanceEnables AI agents to manage performance testing workflows on BlazeMeter's cloud platform through natural language interactions.26Apache 2.0
Related MCP Connectors
Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/perfsage/perfsage-jmeter-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server