specterqa_runLABSCO SUMMARY
Tests that look at the screen, and bill you for it.
The trade is explicit: nothing to maintain when the DOM shifts, but a vision model decides every click, so runs cost money and take time — specterqa_run is synchronous, documented at 45-300s, with a default budget of $5.00 and hard per-run, per-day and per-month caps. What you get back is the kind of finding a selector suite structurally cannot produce, like a disabled submit button with no validation message explaining why.
What it is
A behavioral test runner an assistant can call. You describe personas and journeys in YAML; the engine screenshots the page, asks a Claude vision model what a person like that would do next, and executes the decision through Playwright. There are no selectors, so a layout change does not break the suite — and visual problems a selector test cannot see become findings.
What you get
specterqa_runexecutes a journey against a product and returns step results, findings ranked by severity, and a cost breakdownspecterqa_list_productslists the configured products and the journeys under eachspecterqa_get_resultspulls back the full report of an earlier run by its run IDspecterqa_initscaffolds a new project directory with sample product, persona and journey files- Every run leaves evidence on disk: screenshots, a findings report and a structured JSON result
Requirements
Python 3.10 or later. Install with pip install "specterqa[mcp]" (package specterqa, version 0.4.0), then specterqa install to fetch the Playwright browsers, and start it with specterqa-mcp. ANTHROPIC_API_KEY is required — the vision model does the walking and each run bills against your key. Set SPECTERQA_ALLOWED_DIRS to an explicit allowlist: left unset, the directory parameter of specterqa_run can point anywhere the process can reach.
Setup effort
Follow the published steps — pip install "specterqa[mcp]"
USE CASES
01
Smoke-testing a build before it ships
Run the smoke-tagged journeys and read pass/fail plus findings back in one call.
02
Chasing a UX complaint you cannot reproduce
Send a persona with low tech comfort through the same flow and read where it got stuck.
03
Reviewing an earlier run without paying for it again
Fetch the full report by run ID — steps, findings and cost.
04
Starting a suite from nothing
Scaffold the project directory with sample product, persona and journey files.
4 tools
Listed in project docs. Your client may show a different list.
specterqa_list_productsspecterqa_get_resultsspecterqa_initBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- pip on PATH
- ANTHROPIC_API_KEY in your environment
Where it runs
All 3 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install "specterqa[mcp]"
specterqa installMCP Clients
Claude Desktop, Cursor, Cline
JSON
{
"mcpServers": {
"specterqa": {
"command": "specterqa-mcp",
"args": []
}
}
}The configuration on this page does not set ANTHROPIC_API_KEY; the project's instructions set it with an export line. That line reaches only programs started from the same terminal, so to supply ANTHROPIC_API_KEY, start your client or the server from that terminal.
