Name: BlazeMeter MCP Server
Author: BlazeMeter

LABSCO SUMMARY

A load test from configuration through to its error report, in one place.

The whole lifecycle is covered — upload the script, set concurrency and ramp-up, choose locations, start it, then read the summary, the errors and the request statistics — so "change one thing and rerun" stops meaning a browser tab and a wait. The cost estimate is the part that earns its keep on a credit plan: you can price a configuration before it consumes anything.

What it is

BlazeMeter's own server for its cloud performance-testing platform. It covers the whole hierarchy — account, workspace, project, test, execution — so a load test can be configured, started, watched and reported on without leaving the conversation.

What you get

Tests created and configured: users, duration and ramp-up, geographic distribution, and uploaded scripts and assets
The catalogue of pass/fail rules read, then enabled or disabled on a test
Tests started, execution status followed, and every execution for a test listed
Reports pulled back individually or all at once: summary, error analysis, request statistics, anomaly statistics
AI analysis of a test launched and read back
A cost estimate for a configured run against your allowance type, before the credits are spent
Your own profile with the default account, workspace and project IDs — where everything else starts
Accounts, workspaces and projects listed and inspected, with available test locations, billing usage and test counts
BlazeMeter help categories, articles and curated skills read in place, so product questions get answered from official content

Requirements

BlazeMeter API credentials — an API Key ID and secret, downloaded as api-keys.json. The prebuilt binary reads that file's path from BLAZEMETER_API_KEY and is launched with --mcp; run it once and it prints a ready-made config plus install links for Cursor and VS Code. From source instead, uvx with Python 3.11 or newer. The ghcr.io/blazemeter/bzm-mcp Docker image takes API_KEY_ID and API_KEY_SECRET directly, with SOURCE_WORKING_DIRECTORY bound to your test files. AI consent has to be enabled on the account by its owner. Tool-call traces and metrics are exported by default — OTEL_SDK_DISABLED=true or --no-telemetry stops that, OTEL_EXPORTER_OTLP_ENDPOINT redirects it to your own collector. Behind SSL inspection, point SSL_CERT_FILE at your mounted CA bundle.

Setup effort

Run a container — pull the image and point your client at it

See installation options

USE CASES

01

Getting a new performance test off the ground

Create the test in a project, upload the script and assets, then set the load profile and the locations it runs from.

02

Running it and reading what happened

Start the execution, follow its status, then pull summary, errors and request statistics together.

03

Checking a run fits your credits first

Estimate what the configured test will cost against your allowance type before launching it.

04

Working out why the last run failed

Read the error report and anomaly statistics, and check which failure criteria were enabled on the test.

05

Finding your way around an unfamiliar workspace

Start from your default account, workspace and project, then list what each holds and where tests can run.

06

Answering a BlazeMeter question without leaving the client

Read the official help articles and curated skills in place instead of searching the docs site.

8 tools

Listed in project docs. Your client may show a different list.

blazemeter_user

blazemeter_workspaces

blazemeter_project

blazemeter_tests

blazemeter_execution

blazemeter_billing

blazemeter_help

blazemeter_skills

BEFORE YOU INSTALL

What to know first

Tools you get

8 tools named in the project's documentation.

Requires

BlazeMeter API keys: the binary and uvx setups set BLAZEMETER_API_KEY to the path of the api-keys.json file you download from BlazeMeter; the Docker setup sets API_KEY_ID and API_KEY_SECRET instead
AI consent enabled on your BlazeMeter account

Where it runs

All 3 documented setups run the server on your machine.

INSTALLATION

Connect your client

MCP Clients

Any MCP client — Docker

ANY MCP CLIENT — DOCKER · JSON

{
  "mcpServers": {
    "Docker BlazeMeter MCP": {
      "command": "docker",
      "args": [
        "run",
        "--pull=always",
        "--rm",
        "-i",
        "--mount",
        "type=bind,source=<YOUR_SOURCE_WORKING_DIRECTORY>,target=/home/bzm-mcp/working_directory/",
        "-e",
        "API_KEY_ID=<YOUR_API_KEY_ID>",
        "-e",
        "API_KEY_SECRET=<YOUR_API_KEY_SECRET>",
        "-e",
        "SOURCE_WORKING_DIRECTORY=<YOUR_SOURCE_WORKING_DIRECTORY>",
        "ghcr.io/blazemeter/bzm-mcp:latest"
      ]
    }
  }
}

Any MCP client — binary

Download the zip for your operating system from the Releases page (https://github.com/BlazeMeter/bzm-mcp/releases), extract the binary, and place it in the same folder as your api-keys.json file

Run the binary once. It prints a JSON config and links that add the server to Cursor or VS Code; or paste the block below, with the binary's full path as "command"

ANY MCP CLIENT — BINARY · JSON

{
  "mcpServers": {
    "BlazeMeter MCP": {
      "command": "<YOUR_PATH_TO_BZM_MCP_BINARY>",
      "args": [
        "--mcp"
      ],
      "env": {
        "BLAZEMETER_API_KEY": "<YOUR_BLAZEMETER_API_KEY>"
      }
    }
  }
}

On macOS, if the system blocks the binary as unverified, allow it under System Settings → Privacy & Security, then run it again.

Any MCP client — uvx

ANY MCP CLIENT — UVX · JSON

{
  "mcpServers": {
    "BlazeMeter MCP": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/Blazemeter/bzm-mcp.git@v1.3.1",
        "-q",
        "bzm-mcp",
        "--mcp"
      ],
      "env": {
        "BLAZEMETER_API_KEY": "<YOUR_BLAZEMETER_API_KEY>"
      }
    }
  }
}

BlazeMeter MCP Server