clip.qa is a mobile app that turns screen recordings into structured bug reports. Record a bug on your phone, and clip.qa's AI drafts a report with steps to reproduce and device context for you to review. Reports export as markdown for AI coding tools like Claude Code and Cursor, or to paste into any tracker. Jira, Linear, Slack, GitHub Issues and Notion integrations are coming soon. No SDK required in the app you test.

What is Vibe QA — and why does it matter?

Vibe QA is quality assurance for apps built with AI coding tools — a practice that emerged alongside vibe coding (using AI assistants like Claude Code, Cursor, and Copilot to build apps rapidly). Because vibe-coded apps ship faster than traditional QA can keep up, Vibe QA uses AI-native tools to close the loop: capture bugs visually, generate LLM-ready reports automatically, and feed them back to the same AI tools that built the app. clip.qa is built for Vibe QA.

Does clip.qa work with OpenClaw projects?

Yes. clip.qa produces a structured report your agent, including OpenClaw, can read through MCP or a pasted prompt.

How is clip.qa different from Jam?

Jam has a Chrome extension, a Mac app and an iOS app, plus AI summaries and an MCP server. No Android app is documented. clip.qa records on iOS, Android and in Chrome (beta, request access), with no SDK in the app you test. clip.qa's MCP also records each fix attempt (pending, succeeded, failed) with its commit or PR, and can diff reports.

Do I need to install an SDK or add code to my app?

No. clip.qa works without any SDK integration. It uses your phone's native screen recording, so it works on any app — including competitor apps you're testing, OpenClaw projects, and apps you don't have source access to (subject to OS limits such as FLAG_SECURE).

How much does clip.qa cost?

Free: 30 bug reports and 30 AI-assisted reports a month. Team ($12.99/mo or $129/yr, billed per creator seat, viewers free): unlimited bug reports, 200 AI-assisted reports and 50 share links a month. Enterprise pricing is custom; confirm current quotas and features with sales. Audit logs and priority support are listed; SAML/SSO is coming soon.

What platforms does clip.qa support?

The clip.qa web dashboard is available now; the iOS app, Android app and Chrome extension are in beta (request access at hello@clip.qa). Bug reports can be copied as markdown into any tracker (Jira, Linear, GitHub Issues; native integrations coming soon) or used directly as prompts for Claude, Cursor, and other AI coding tools.

MCP Servers for an AI Coding Workflow

An AI coding workflow can use one MCP server to bring bug reports into the agent and another to search saved knowledge. The clip.qa MCP server gives agents access to reports and their evidence, while KnowMan provides search across saved articles, links, and memories.

Tools3 min read

clip.qa team November 10, 2026

Give your coding agent useful context

An agent can work with more than the code in its current task. It can also use bug reports and saved knowledge when those sources are available through MCP servers.

clip.qa connects bug reports to AI tools. KnowMan saves articles and links, searches them by meaning, answers questions with citations, and keeps memories such as claims, decisions, and playbooks.

Bring bug reports into the agent

A screen recording can show what happened, but the agent needs a report it can read. clip.qa turns recordings into structured bug reports for review and for AI coding tools. It records device context, and Chrome extension reports can include console and network requests.

The clip.qa MCP server lets an agent read reports, screenshots, video transcripts, frame analysis, and report differences. For Chrome extension reports, it can also read console logs and network requests. Reports stay private until explicitly shared, and PII is scrubbed from MCP output.

See how clip.qa turns a screen recording into a bug report for the capture-to-report flow.

Add saved knowledge as a separate source

Bug reports describe a specific issue. Saved articles and notes can provide background the agent can search when a question calls for it. KnowMan is the knowledge-side MCP server: it searches saved items by keyword or meaning, answers questions with citations, and can save a URL with an optional note.

Learn more about KnowMan and the MCP servers for an AI coding workflow. KnowMan is a separate place to keep and search written notes.

Choose the server setup that fits

clip.qa offers a remote MCP server using Streamable HTTP at https://mcp.clip.qa/mcp. Sign in through a browser using OAuth 2.1 and PKCE. Its page documents setup for Claude Code, Cursor, and Windsurf. It also offers a local npm package configured with a clip.qa API key.

KnowMan offers a hosted remote MCP server at https://api.knowman.io/mcp and a local stdio server. The remote server supports OAuth sign-in or an API key. The local server runs with npx -y @knowman/mcp and requires Node 22 or newer.

Ask the agent for the right source

Use clip.qa when the task concerns a captured bug report and its evidence. Use KnowMan when the agent needs to search saved items, retrieve one item, answer from saved knowledge with citations, or find a saved memory.

Keep the request specific. Ask the agent to inspect a clip.qa report for the issue, or search KnowMan for a relevant saved article or decision. Each server gives the agent access to its own source of information.

Give your agent the context it needs

Connect clip.qa over MCP to bring bug reports and evidence to your AI tool.

Key takeaways

An agent can work with more than the code in its current task.

A screen recording can show what happened, but the agent needs a report it can read.

Bug reports describe a specific issue.

clip.qa offers a remote MCP server using Streamable HTTP at https://mcp.clip.qa/mcp.

Use clip.qa when the task concerns a captured bug report and its evidence.

Frequently asked questions

What does the clip.qa MCP server provide?

It lets an agent read bug reports, screenshots, video transcripts, frame analysis, and report differences. For Chrome extension reports, it can also provide console logs and network requests.

What does the KnowMan MCP server provide?

It searches saved items by keyword or meaning, answers questions with citations, reads one saved item, saves URLs, lists recent items, and searches saved memories.

Can I use both MCP servers in one coding workflow?

Yes. They provide separate sources: clip.qa provides bug reports and related evidence, while KnowMan provides access to saved articles, links, and memories.

How do I connect clip.qa over MCP?

Use the remote server at https://mcp.clip.qa/mcp and sign in through a browser with OAuth 2.1 and PKCE. clip.qa also documents a local npm package configured with an API key.