Perfscale MCP
OfficialClick 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., "@Perfscale MCPrun a load test on my API with 100 virtual users for 5 minutes"
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.
perfscale MCP servers
Model Context Protocol servers for perfscale:
Package | Server | Use case |
| Local: run k6/locust/native load tests, lint and manage test/config YAML via the OSS | |
| Cloud: machines, tests, runs, metrics, and audit data from perfscale.su / perfscale.ru |
Quick start
OSS (local)
Requires the perfscale CLI on PATH (or PERFSCALE_BIN).
{
"mcpServers": {
"perfscale": {
"command": "npx",
"args": ["-y", "@perfscale/mcp"]
}
}
}Tools: run_test, lint, get_schema, parse_summary, list_actions,
list_configs, read_config, write_test, write_config, update_config,
remove_config.
Controlplane (cloud)
Create an API token in the dashboard (Settings → API Tokens; Scale plan: 1 per user, Enterprise: 5 per user), then:
{
"mcpServers": {
"perfscale-cloud": {
"command": "npx",
"args": ["-y", "@perfscale/controlplane-mcp"],
"env": {
"PERFSCALE_API_URL": "https://perfscale.su",
"PERFSCALE_API_TOKEN": "psk_..."
}
}
}
}Tools: whoami, limits, usage, list_machines, get_machine,
list_tests, get_test, write_test, list_configs, write_config,
list_runs, get_run, get_run_logs, runs_by_machine, run_test,
metrics_catalog, query_metrics, get_otel_timeseries, list_dashboards,
list_git_repos, sync_git_repo, list_env_vars (values masked),
audit_log.
Every tool call is metered against the workspace's monthly AI tool-call
budget — usage shows where you stand, limits shows the plan.
Composite mode (workspace MCP servers)
By default the server also aggregates the remote MCP servers attached to
your workspace (dashboard → Settings → AI → MCP Servers): their tools
appear next to the core ones, prefixed with the server's name (grafana →
grafana_search_dashboards), and calls are proxied through. Only remote
transports are supported (streamable HTTP, SSE fallback) — never local
commands. Resolving the attached servers requires an admin token: header
values are secrets, so a regular member's token gets the core tools only. A
remote that is down is skipped with a warning; the core surface always
works. Set PERFSCALE_MCP_COMPOSITE=off to force the plain core server.
Related MCP server: k6 MCP Server
Development
pnpm install
pnpm test # vitest across all packages
pnpm build # tsc -b per packageReleasing
Bump the version in the package's package.json, then tag and push:
git tag v0.2.0 && git push origin v0.2.0CI publishes to npm (release.yml); packages whose version is already on
the registry are skipped, so packages version independently. Requires the
NPM_TOKEN repo secret.
This server cannot be installed
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
AlicenseNot gradedqualityBmaintenanceEnables AI agents to manage performance testing workflows on BlazeMeter's cloud platform through natural language interactions.26Apache 2.0- FlicenseNot gradedqualityDmaintenanceEnables running k6 load tests with customizable duration and virtual users via natural language, with real-time output and LLM-powered analysis.1
- AlicenseNot gradedqualityDmaintenanceEnables AI models (Claude, ChatGPT, GitHub Copilot) to run and analyze local tests, rerun failures, and orchestrate QA workflows using existing UI and API test frameworks.7MIT
- AlicenseNot gradedqualityCmaintenanceConverts non-functional requirements and code into secure, traceable JMeter performance tests with coverage analysis, plan generation, execution, and GitHub draft PRs.10MIT
Related MCP Connectors
Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.
Connect to PlanetScale databases, branches, schema, query insights, and execute SQL
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
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/Perfscale/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server