BlazeMeter MCP Server

MCP Server for AI-driven BlazeMeter performance testing

The BlazeMeter MCP Server connects AI tools directly to BlazeMeter's cloud-based performance testing platform. This gives AI agents, assistants, and chatbots the ability to manage complete load testing workflows from creation to execution and reporting. All through natural language interactions.

[!NOTE]
For detailed documentation including use cases, available tools, integration points, and troubleshooting, see theBlazeMeter MCP Server documentation.

- BlazeMeter API credentials (API Key ID and Secret)
- ComplyBlazemeter AI Consent
- Compatible MCP host (VS Code, Claude Desktop, Cursor, Windsurf, etc.)
- Docker (only for Docker-based deployment)
- uvand Python 3.11+ (only for installation from source code distribution)

Follow theBlazeMeter API Keys guideto obtain your API keys as JSON.

[!IMPORTANT]
When downloading your API keys from BlazeMeter, save theapi-keys.jsonfile in the same folder where you'll place the MCP binary.

The easiest way to configure your MCP client is using our interactive CLI tool:
- Download the appropriate binaryfor your operating system from theReleasespage

[!NOTE]
Choose the binary that matches your OS (Windows, macOS, Linux)
- Place the binaryin the same folder as yourapi-keys.jsonfile
- Execute or Double-click the binaryto launch the interactive configuration tool
- The tool automatically generatesthe JSON configuration file for you

[!IMPORTANT]
For macOS: You may encounter a security alert saying "Apple could not verify 'bzm-mcp-darwin' is free of malware." To resolve this:
- Go toSystem Settings→Privacy & Security→Security
- Look for the blocked application and click"Allow Anyway"
- Try running the binary again

Manual Client Configuration (Binary Installation)
- Download the binaryfor your operating system from theReleasespage
- Run the binary once— it will print a JSON config andclickable linksto add this MCP in Cursor or VS Code.
- Or configure your MCP client manuallywith the following settings:

{ "mcpServers": { "BlazeMeter MCP": { "command": "/path/to/bzm-mcp-binary", "args": ["--mcp"], "env": { "BLAZEMETER_API_KEY": "/path/to/your/api-key.json" } } } }

Manual Client Configuration (From Remote Source Code)
- Prerequisites:uvand Python 3.11+
- One-click installor configure your MCP client manually:

{ "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": "/path/to/your/api-key.json" } } } }

[!NOTE]
uvx installs and runs the package and its dependencies in a temporary environment.
You can change to any version that has been released or any branch you want. Package support for uvx command is supported from version 1.0.1 onwards.
For more details on the uv/uvx arguments used, please refer to the officialuv documentation.

{ "mcpServers": { "Docker BlazeMeter MCP": { "command": "docker", "args": [ "run", "--pull=always", "--rm", "-i", "--mount", "type=bind,source=/path/to/your/test/files,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=/path/to/your/test/files", "ghcr.io/blazemeter/bzm-mcp:latest" ] } } }

[!IMPORTANT]
For Windows OS, paths must use backslashes (\) and be properly escaped as double backslashes (\\) in the JSON configuration.
E.g.:C:\\User\\Desktop\\mcp_test_folder

[!NOTE]
In order to obtain theAPI_KEY_IDandAPI_KEY_SECRETrefere toBlazeMeter API keys

{ "mcpServers": { "Docker BlazeMeter MCP": { "command": "docker", "args": [ "run", "--pull=always", "--rm", "-i", "--mount", "type=bind,source=/path/to/your/test/files,target=/home/bzm-mcp/working_directory/", "-v", "/path/to/your/ca-bundle.crt:/etc/ssl/certs/custom-ca-bundle.crt", "-e", "SSL_CERT_FILE=/etc/ssl/certs/custom-ca-bundle.crt", "-e", "API_KEY_ID=your_api_key_id", "-e", "API_KEY_SECRET=your_api_key_secret", "-e", "SOURCE_WORKING_DIRECTORY=/path/to/your/test/files", "ghcr.io/blazemeter/bzm-mcp:latest" ] } } }

- /path/to/your/ca-bundle.crtwith your host system's CA certificate file path
- The container path/etc/ssl/certs/custom-ca-bundle.crtcan be any path you prefer (just ensure it matchesSSL_CERT_FILE)

TheSSL_CERT_FILEenvironment variable must be set to point to your custom CA certificate bundle. Thehttpxlibraryautomatically respects theSSL_CERT_FILEenvironment variablefor SSL certificate verification.

BlazeMeter MCP reports traces and metrics for MCP tool calls usingOpenTelemetry. This gives you visibility into which tools are used, how long they take, and when errors occur.

"env": { "OTEL_SDK_DISABLED": "true" }

"-e", "OTEL_SDK_DISABLED=true"

"args": ["--mcp", "--no-telemetry"]

Use these environment variables to point at a different OpenTelemetry collector (for example, a local one during development):

gRPC example (typical local collector on port 4317):

"env": { "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4317", "OTEL_EXPORTER_OTLP_PROTOCOL": "grpc" }

HTTP example (typical local collector on port 4318):

"env": { "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318", "OTEL_EXPORTER_OTLP_PROTOCOL": "http/protobuf" }

When running the binary directly, you can override the endpoint and headers with CLI flags instead of environment variables:

"args": [ "--mcp", "--otel-endpoint", "http://localhost:4317", "--otel-headers", "Authorization=Bearer token" ]

- Traces— one span per call with the tool name, action, MCP client name and version, session ID, and error type when applicable.
- Metrics—mcp.tool.calls(count) andmcp.tool.duration(seconds), broken down by tool and action.

Security tokens and other credentials are not included in telemetry data.

If your MCP client sendstraceparentortracestatein the request metadata, BlazeMeter MCP links its spans to that parent trace.

This project is licensed under the Apache License, Version 2.0. Please refer toLICENSEfor the full terms.

- MCP Server Documentation:BlazeMeter MCP Server Guide
- API Documentation:BlazeMeter API Documentation
- Issues:GitHub Issues
- Support: Contact BlazeMeter support for enterprise assistance

Read-first Jenkins MCP server in Go for agent-driven build debugging. 20 tools including compare_builds, flaky-test detection, JUnit/Ginkgo failure parsing, and disk-cached console logs with on-disk path handoff. Write tools (trigger/stop/cancel) gated by JENKINS_MCP_READONLY env var.