
ProdPoke
A hosted QA tester that runs real Playwright browser sessions from your MCP client. You chat with it in plain English to scan URLs for accessibility, SEO, performance, and broken flows. It exposes two tools: `chat` for stateful testing conversations (you pass a `session_id` to build on prior scans) and `get_credit_balance` to check your account. Nothing installs locally. You authenticate with a bearer token, point your client at prodpoke.com/v1/mcp, and the service spins up headless Chromium on their infrastructure. Findings come back structured by severity and category. Useful when you want to automate QA checks without managing browser containers or parsing HTML yourself.
- GitHub stars
- 1
- tools
- 2
- auth
- Secret needed
- transport
- HTTP
- last updated
- Apr 22, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
chatTalk to ProdPoke like a QA tester — scan a URL, test a flow, investigate findings, set session preferences. Stateful via session_id.
Talk to ProdPoke like a QA tester — scan a URL, test a flow, investigate findings, set session preferences. Stateful via session_id.
No parameter schema in public metadata yet.
get_credit_balanceCheck your remaining scan credits.
Check your remaining scan credits.
No parameter schema in public metadata yet.
Sponsors
Readme
ProdPoke MCP Server
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.
Landing page · Get an API key · Pricing · ProdPoke
ProdPoke MCP demo — scanning a site from Claude Desktop
What it does
Details
- Repository
- github.com/prodpoke/prodpoke-mcp
- Website
- prodpoke.com/mcp
- Categories
- Sales & Marketing, Communication & Messaging
- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active