start_recording
Start a recording session that keeps recording while you work (drive the page with your own browser tools, run commands, …). Accepts type, storageState / userDataDir+profileDirectory / initScript, and exposeCdp (get a CDP endpoint + in-page window.clipyMark/window.clipyChapter bridge to drive the re
How to use it
Project documentation lists start_recording for the Clipy MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Clipy MCP
npx -y @clipy/mcpOther tools in Clipy MCP (22)
Discard the active session; nothing is uploaded.
Drop a === CHAPTER: <label> === boundary into the active session — split a recording into named sections (ideal for before/after demos).
Drop a narration marker into the active session (live clock, or backdate with atSeconds) — markers become the recording's transcript chapters. Can carry evidence in one of two provenances: clipy-verified (assertSelector / assertText / assertUrl) where Clipy checks the page itself, or driver-attested
assertSelector / assertText / assertUrl
Download the MP4 locally so you can clip it or extract frames yourself (e.g. with ffmpeg).
observed + verdict (both required)
The full agent-context bundle (summary + key moments + transcript + available browser diagnostics) as markdown.
Privacy-redacted visited routes, console warnings/errors, page exceptions, and failed fetch/XHR metadata. The evidence is explicitly labelled page-reported; headers, bodies, cookies, tokens, typed values, and raw query values are never captured.
One context document's metadata: source, duration, tags, the server's classification (video type, whether visual evidence is needed, planned moments), and which transcript/frames exist. Not the transcript itself.
Key moments: timestamps, captions, and click coordinates.
Metadata for one recording (status, duration, transcript/summary status).
The AI summary: TL;DR, key points, action items.
The full timestamped transcript + plaintext.
List the user's context documents — YouTube videos and local video files they imported with clipy context import, so agents can read them. A separate library from their own screen recordings.
List your most recent recordings.
Read a context document as compiled markdown — header, metadata, then the timestamped transcript with frame captions interleaved. Takes startMs/endMs so you can walk a two-hour video section by section instead of flooding your context.
Record a web app headlessly and upload it as a Clipy recording; returns its share + agent-context URLs. Accepts a type (recording kind), viewports (sweep several screen sizes into one video), storageState / userDataDir+profileDirectory / initScript (record behind a login), and timestamped notes that
Replace a recording's transcript with text you author (needs the ingest scope). Call gettranscript first and pass its revision; stale replacements are rejected instead of overwriting a concurrent edit. The summary regenerates automatically. Marked as agent-edited, never passed off as speech-to-text.
Search the whole Clipy memory at once — every screen recording the user made and every video they imported — returning the matching moments with timestamps and a URL that opens at that point. Matching is semantic as well as literal, so "login flow" finds a moment where someone said "the authenticati
Search your recordings by keyword (title + description).
Finish the session: close the browser, upload, return the share + agent-context URLs.
Poll until a recording's transcript/summary finish processing.