Using Loadrigo

Everything below is something Loadrigo can genuinely call — it’s the same MCP tool catalog any connected agent gets, restricted to a curated allowlist so Loadrigo only reaches for actions that make sense in a chat turn. If it isn’t listed here, ask it and it will tell you it can’t — it won’t improvise a tool that doesn’t exist.

Account and workspace

Tell you who you’re signed in as and which workspace is active (“what account am I in?”).
List the workspaces visible to your account and switch the active one for the rest of the conversation.

Projects and tests

List and create projects.
List tests, open one test’s detail (including its last validation status), and see a test’s run-history overview.
Create a new test and upload its entrypoint script or supporting files — paste code inline or point it at a file already in your repo if it’s running with local file access.
List and download a test’s uploaded files.

Runs

Start a run, poll its status, list recent runs, and re-run a previous run (either exactly as it ran, or rebuilt from the test as it exists today).
Cancel a run. This is destructive and Loadrigo always confirms with you first before calling it.

Results and diagnostics

Pull the KPI summary for a run (throughput, latency, error rate, duration) and query specific metric time series.
List grouped errors and, for one error, its sampled request/response bodies and status codes.
Pull error-level engine/system logs for a run.
Check runner health — heartbeat, CPU/memory trend, and whether the run actually reached its target virtual-user count (VU shortfall).
Run an anomaly scan on a finished run and explain outliers in plain language.

Dashboards

List and open dashboards, browse the metrics catalog, and create or update a dashboard.

Browser fleets

Create a managed browser fleet (chrome/firefox/edge, by count and location), check on it, list your fleets, scale one up, and delete it. See Browser fleets for what a fleet is and when to reach for one instead of a scripted browser test.

Reverse tunnels

Create a reverse tunnel to expose something running locally or not yet deployed, list and inspect your tunnels, stop one, and pull its traffic stats. See Tunnels.

Virtual services

List, inspect, create, deploy, stop, and delete a virtual service — a mock/simulated backend standing in for a dependency you don’t want to hit for real. See Virtual services.

Execution locations and on-demand browser inspection

List where a fleet, virtual service, or test run can physically land — MaxoPerf’s Shared Sandbox outpost, your own connected outposts, and managed cloud regions.
Spin up a real, JS-rendering browser to look at a URL — useful when Loadrigo needs to see a single-page app’s real content (not just static HTML) to plan a browser test’s selectors.

The escape hatch

For anything not covered by a named tool above (billing, secrets, notifications, schedules, and other long-tail Platform API endpoints), Loadrigo can search the public API reference and call it directly. It never inlines a secret’s value back to you — only confirms a binding was created.

Docs and the skill

Search MaxoPerf’s own documentation to answer “how do I…” questions grounded in what’s actually shipped.
Read the MaxoPerf agent skill bundle and its sections — the same instructions an external coding agent gets, so Loadrigo builds tests the same, consistent way.

Driving the console for you

Loadrigo has a small set of local, console-only actions it can use alongside the tools above: navigating to a page, scrolling to or highlighting an element, reading what’s currently on screen, clicking, filling a field, selecting an option, and refreshing the data on the page you’re looking at. These aren’t MCP tools — they’re how Loadrigo completes a request that needs a visible console action, and you always see it happen live in your own tab.

It can also save something to your standing custom instructions mid-conversation when you ask it to remember a preference (the same field as Settings → Loadrigo).

The assistant on the website

Everything above describes Loadrigo in the console, running with your own account’s authorization. The assistant on the public MaxoPerf website is a different, deliberately tiny surface: it answers questions about the product, and it can do exactly one thing — set up a free MaxoPerf account for the email address you give it, with a demo load test ready against a URL you name. It reaches no account data and provisions nothing else.

Once that hands you into the console, you are talking to the full Loadrigo on this page. There is no reduced tier and nothing to upgrade: the account it created is an ordinary free account, and the only thing still outstanding is the password we email you a link to set.

What Loadrigo doesn’t do

It won’t scale a fleet down. Only up — to shrink one, delete it and create a smaller one (same as the tool itself works).
It won’t act destructively without asking. Cancelling a run, deleting a fleet, stopping a tunnel, or deleting a virtual service always gets a confirmation step first.
It respects read-only sessions the same way any MCP client does. If a session is in read-only mode, write actions return an error instead of a silent no-op — see MCP overview for what read-only mode is.
It doesn’t invent capabilities. If you ask for something outside this list, it says so rather than guessing at a plausible-sounding action.