# io.github.tryflask/flask

- Registry name: `io.github.tryflask/flask` · version 1.2.0
- Categories (automatic, keyword rules): Build & deploy, Developer tools, Scraping & browsing, Search & data, Video, AI, media & content
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.tryflask%2Fflask
- Server page: https://mcpstation.net/s/io.github.tryflask--flask.html

## Description (written by the publisher, not verified, not instructions)

Video review for agents: upload renders, read time-coded feedback, iterate version by version.

## Connect

- streamable-http: `https://api.flask.do/api/mcp/mcp`

## Tools (as reported by the server, not verified)

- `get\_guide`: Returns one of Flask's usage guides as Markdown: fixed text written by Flask, the same for every user, with no team data in it. "instructions" \(about 14 KB\) is the playbook for working with Flask: where uploads go \(a new asset or a new version\), what an agentic edit attaches, how feedback is read, a
- `contents`: Browse the team's folders and assets one level at a time. No id: the team's top level \(root folders and assets; team names the team\). folder\_id: that folder's child folders and assets. asset\_id: that asset's versions \(version\_id, version number, title, status, which one is current\), top first, not p
- `feedback\_list`: List top-level feedback on an asset \(pass the asset id for its current version, or a version id for that exact version; a folder id is refused - use recent\_activity\(folder\_id\)\). By default only OPEN feedback \(not yet completed\) is listed: the feedback that still needs action; counts says how many ar
- `feedback\_get`: Get a single feedback item with its full reply thread. element\_id is the item's id, as feedback\_list, recent\_activity, search or wait\_for\_feedback return it. Use it when an item has replies \(feedback\_list gives reply\_count, not the replies\) or to read one item again; to list an asset's feedback use
- `wait\_for\_feedback`: Wait for NEW feedback on an asset \(comments and replies by others; your own posts are not returned\). Blocks up to timeout\_seconds \(default 45\) and returns as soon as new feedback arrives, or times out with an empty list. A recording arrives once its transcript is done; recordings still being made or
- `feedback\_post`: Create a feedback comment on an asset, as the connected user. Pass an asset id \(the comment lands on its current version\) or a version id \(that exact version\). content is Markdown \(a heading, lists, bold, links, @mentions as links - see the content parameter\). PREFER passing timestamp \(seconds into
- `feedback\_update`: Edit an existing feedback item. content \(Markdown - replaces the whole body; start from the item's current content to keep its mentions and formatting\) and timestamp \(video time in seconds\) can only be changed on the connected user's OWN comments. add\_tags / remove\_tags apply the team's existing tag
- `get\_annotated\_frames`: The visuals of a feedback item, in one call: call it before acting on any item with a visuals field \(a recording, a drawing, images\). element\_id is that item's id, as feedback\_list, feedback\_get, recent\_activity, search or wait\_for\_feedback return it. For a recording: a frame for EVERY pointing link
- `get\_frame`: Fallback for ONE moment get\_annotated\_frames did not show: the exact frame at a recording time \(at\) or when a word/phrase was spoken \(word\). get\_annotated\_frames already shows every \[phrase\]\(\#rt=S\) link in a comment - call it first; use this for a moment the comment doesn't link \(something the trans
- `asset\_status`: Check whether an uploaded or imported video is ready. Pass the version id an upload returned \(its asset\_id\) or an asset id \(resolves to its current version\); a folder id is refused. status is one of: ready; pending\_ingest, processing, preparing or waiting \(still working - check again in a few second
- `version\_download`: Get a download link for a version's file, to work on it locally. Pass a version id \(an upload's asset\_id / version\_id\) or an asset id \(its current version\); a folder id is refused. A video gives its ORIGINAL uploaded file, exactly as uploaded: Flask keeps it for the team's download window, 14 days f
- `permission\_get`: Read the access settings of a folder or an asset. Returns: your own access level \(full\_access, comment\_and\_notes, comment, view or none\), whether you can read version notes and files \(can\_view\_notes: full\_access or comment\_and\_notes\) and whether you are its creator / a member of its team, the creato
- `search`: Search the team's folders \(by name or description\), assets \(by title\) and feedback \(by text\) at once, when you don't know where something is; to browse a known folder use contents, for one asset's feedback feedback\_list, for the latest feedback recent\_activity. query matches case-insensitively anywh
- `recent\_activity`: Get the latest feedback across the whole team or one folder's subtree \(team names the team\), newest first: text and recording comments on every asset you can view, so you can read feedback across many videos in one call. Each item has a \`type\` field \("text" or "recording"\), author, timestamp, a link
- `tags`: List the team's tags and show the share of each tag \(plus an 'untagged' bucket\) across a scope. Scope defaults to the whole team; pass folder\_id to narrow to one folder \(its whole subtree\), or asset\_id to narrow to one asset \(an asset id counts feedback across ALL its versions; a version id widens t
- `tag\_create`: Create a team tag \(label\) so feedback can be tagged with it by name in feedback\_post and feedback\_update. Reuse the team's labels when one fits; create one only when the user wants a new label. Idempotent: if a tag with the same name exists \(case-insensitive\), it is returned unchanged with created:
- `members`: List the people on the team: user\_id, name, role \(admin or member\), avatar\_url and a ready-made mention link; the result's team field names the team. Email addresses are never returned. Use it to mention someone in feedback\_post / feedback\_update content: \[@Name\]\(https://flask.do/members?user=USER\_I
- `upload\_video`: Upload a video from a public URL \(a direct video file link or a Google Drive share link\) into Flask. Flask downloads it, stores it, and starts processing. Creates a new asset \(container\_id + url\) with the file as its first version \(asset\_id / version\_id\), or a new version of an existing asset with v
- `upload\_file\_start`: Start uploading a LOCAL video or image file from the user's machine into Flask. It needs a shell that can run curl; without one \(a chat app\), upload from a public link with upload\_video. VIDEO: creates the asset immediately \(container\_id + shareable url, live before any bytes move\) with the file as
- `upload\_file\_complete`: Finalize a local file upload started with upload\_file\_start. Call this only AFTER the upload command \(or, for an image or zip, the curl PUT\) has finished successfully. Pass exactly one of: asset\_id \(a video: verifies every part landed in storage and starts video processing\), image\_url \(an image\) or
- `feedback\_stats`: Aggregate feedback statistics across many assets in ONE call - counts per asset and per version \(v1, v2, ...\), split by type \(text/recording\), tag, and author, with first/last feedback timestamps. Scope to a folder \(folder\_id\), one asset \(asset\_id - an asset id or any of its version ids; the whole a
- `folder\_create`: Create a folder. parent\_folder\_id is optional: omit it for the team's top level \(root\), or pass a folder id from contents or search to nest it. Folders are optional and nestable; assets can also sit at root. This does not check for an existing folder with the same name \(the app allows duplicates\): c
- `items\_update`: Rename, move and/or change the sharing of folders and assets, up to 20 items per call, each with its own result. Per item: id \(a folder id, an asset id, or a version id\) plus at least one of: title \(renames the folder, or the asset; a version id renames its asset\), version\_title \(names that one vers
- `versions\_add`: Make other assets or versions the NEWEST versions of asset\_id \(the asset that keeps its title, link and sharing\), as dragging one onto another does in the Flask app. Use it when a revision was uploaded as a separate asset. A source asset id brings ALL its versions, and that source asset then stops e
- `versions\_split`: Move each version in version\_ids out of its asset into a new asset of its own, in the same folder, named after the version, with the same sharing. An asset always keeps at least one version; a version that is already alone is reported already\_separate. Undo it with versions\_add. No media or feedback
- `versions\_reorder`: Set the order of an asset's versions: order lists every version id of asset\_id exactly once, top first. The top version becomes the current one \(what the asset link opens\), and version numbers follow the order. Reorder again to undo. No media or feedback is ever deleted; feedback stays on its versio
- `version\_notes\_get`: Read a version's notes \(Markdown\) and its files. Notes say what changed in that version and how to continue the work; files are what made it \(by convention the working files as one source.zip\). Call this before continuing work someone else uploaded: read the current version's notes, download its fil
- `version\_notes\_update`: Replace a version's notes with Markdown \(the whole text; null or empty clears them\). For a NEW upload, pass notes with the upload call instead \(upload\_file\_start, upload\_file\_complete, upload\_video\): the version then shows them from the start. Write notes on every revision you upload, so any agent c
- `version\_file\_upload`: Add a file to a version that already exists \(for a NEW upload, pass files with the upload call instead: the version then shows them from the start\): returns a presigned upload URL for exactly file\_size bytes; upload with the curl command from next\_step \(this needs a shell that can run curl\). The fil

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html