AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.
io.github.prodpoke/prodpoke-mcp (MCP Server)
The io.github.prodpoke/prodpoke-mcp server is an AI QA tester that uses real Playwright browsers to scan websites for bugs. It’s used via chat with MCP clients (e.g., Claude, Cursor) and can remember context across turns.
🛠️ Key Features
Real browser scanning using Playwright
Bug detection during website scans
Remembers what you talked about across turns
MCP protocol support (Streamable HTTP)
🚀 Use Cases
QA testing workflows for websites
Scanning for issues during SEO-oriented reviews
Checking accessibility-related problems
Identifying performance issues
⚡ Developer Benefits
Works with any MCP client via configuration (hosted, not installed)
Uses Model Context Protocol for chat-driven QA
Integrates browser automation into an MCP tool flow
⚠️ Limitations
Hosted-only deployment; requires pasting configuration into an MCP client
A QA tester inside your AI. Chat with ProdPoke from Claude, Cursor, or any MCP
client. It launches real Playwright browsers, finds real bugs, and remembers what
you talked about across turns.
Hosted, not installed. Just paste a config into your MCP client and go.
ProdPoke MCP demo — scanning a site from Claude Desktop
What it does
ProdPoke is a remote, stateful MCP server that runs real-browser QA for any website. You
describe what you want in plain English; ProdPoke spins up a headless Playwright session,
navigates the site, and streams back structured findings — accessibility, SEO,
performance, user-flow bugs, visual regressions, broken CTAs, and more.
Unlike local tools, everything runs on ProdPoke infrastructure. No Chromium to install,
no browser containers to manage, no cleanup.
Available tools
Tool
Description
Parameters
chat
Talk to ProdPoke like a QA tester — scan a URL, test a flow, investigate findings, set session preferences. Stateful via session_id.
message (required), session_id (optional)
get_credit_balance
Check your remaining scan credits.
—
Example chat response
json
{"session_id":"a1b2c3d4-...","response":"Found 3 issues on https://example.com...","findings":[{"severity":"high","category":"accessibility","title":"Missing alt text on 4 images","description":"Images in the hero section lack alt attributes..."},{"severity":"medium","category":"seo","title":"Missing meta description","description":"The page has no meta description tag..."}],"session_context":{"url_being_tested":"https://example.com","message_count":2,"has_findings":true}}
Setup
1. Get your API key
Sign up for a ProdPoke account — the free tier
includes 500 credits, enough for a first scan.
The chat tool is stateful. Each response includes a session_id; pass it back to continue
the conversation with full context:
chat("Scan https://mysite.com") — starts a session, runs the scan, returns session_id + findings.
chat("Dig deeper into the accessibility issues", session_id="...") — builds on the prior scan.
chat("Now test the checkout flow", session_id="...") — runs a targeted test, knows about the earlier findings.
chat("What should I fix first?", session_id="...") — answers from the accumulated session context.
Sessions persist across MCP client restarts for the lifetime of the key.
How it works
code
Your MCP client ──Authorization: Bearer pp_...──▶ https://prodpoke.com/v1/mcp
│
▼
Orchestrator classifies intent
│
▼
Playwright worker on ProdPoke
infrastructure runs the scan
│
▼
Findings streamed back as a
structured `chat` response
Nothing is installed on your machine. Scans run on our servers. You pay per scan in
credits (see below).
Pricing
Plan
Credits
Price
Free tier
500 credits
$0
Watch
10,000 / month
$15 / month
Watch Pro
50,000 / month
$49 / month
Top-up packs
1,000 – 50,000
From $3
A standard scan costs roughly 10 credits. Deeper workflows — full user-flow tests,
competitor comparisons — run 400–500 credits. See full pricing →
The error message when you're out of credits is explicit: "Insufficient credits. You need N but have M.", so your AI client can surface it clearly.
Troubleshooting
401 Missing Authorization header — your client didn't send the Authorization
header. Double-check the config (the key goes in headers, not env, for streamable HTTP).
401 Invalid or revoked API key — the key was revoked or typed incorrectly. Re-mint at
/app/settings/keys.
The tool responds but never runs a scan — ask it to scan a specific URL. ProdPoke
needs a URL to launch a browser; it won't guess.
Scan hangs for >2 minutes — the MCP call times out at 120 seconds per step. Long
flows should be split into multiple chat turns using session_id.