Flask MCP Integration

Connect Flask to Claude and other AI assistants via the Model Context Protocol.

How to connect

In Claude (claude.ai or Claude Code), open the connector / integration settings and add a new MCP server.
Use the connection details below. You'll be redirected to Flask to authorize access to your team.
Once connected, ask Claude things like “summarize the feedback on our latest cut” or “what has the team been working on this week?”

Server URL	https://api.flask.do/api/mcp/mcp
Authentication	OAuth 2.0 with Dynamic Client Registration (RFC 7591)
Transport	Streamable HTTP (POST only — SSE not supported)
Capabilities	Read + video upload — reads your data and can upload videos (from a URL or a local file); it cannot edit or delete anything
Requirements	Free or paid Flask account

Available tools

Every tool is read-only except the upload tools — upload_video imports a video from a URL, and upload_file_start / upload_file_complete upload a local file from your machine, always into a folder you can edit. The MCP never edits or deletes folders, assets, feedback, or tags.

Browse

contents — list root-level project folders, or open a folder to see its child folders and assets

Feedback

feedback_list — list top-level feedback on an asset (text comments + voice/screen recordings), each with its tags by name
feedback_get — get a single feedback item with its full reply thread, including the AI summary and the transcript for that recording segment; pass transcript: "full" for the recording's complete transcript
wait_for_feedback — long-poll that returns new feedback the moment it's left (blocks up to ~45s per call); lets agents listen for your review in near real time instead of polling

Every feedback item includes its tags as readable names. Recordings are split into segments — each carries the transcript for its own segment plus a play_url, a deep link that opens the recording at the right moment.

Search & activity

search — unified search across folders, assets, and feedback in one call
recent_activity — the latest feedback (text + recording) across the whole team, newest first

Tags & permissions

tags — list the team's tags and the share of feedback each tag covers, scoped to the team, a folder, or a single asset
permission_get — see who has access to a folder and at what level

Media

asset_status — check the processing status and progress of a video asset
upload_video (write) — import a video into a folder from a public URL (direct file link or Google Drive); returns an asset to poll with asset_status
upload_file_start (write) — start uploading a local video file (up to 5GB); returns the shareable link immediately plus a presigned upload URL
upload_file_complete (write) — finalize a local upload and start processing; the video is watchable via preview playback while it processes

All upload tools accept version_of to upload as a new version of an existing asset (or version stack) instead of a separate asset — the stack's link always shows the newest version.

Use cases

Catch up on team feedback

See what your team has been giving feedback on, with links to jump into each conversation.

“What feedback did my team leave this week?”

Summarize feedback on a video

Get a structured summary grouped by theme, with verbatim quotes, timestamps, and clickable links back to each item.

“Summarize all the feedback on the ‘loading screens’ cut and group it by theme”

Turn voice notes into action items

AI transcripts of every voice/screen recording mean Claude can pull concrete action items straight out of casual feedback.

“Pull every action item from the voice recordings on the latest cut”

Upload a video from your workflow

Hand Claude a link or a local file — a finished cut, an agent-rendered video — and have it uploaded straight into the right folder, ready for feedback. The share link works immediately.

“Upload this Drive link to the ‘Q3 launch’ folder and tell me when it’s ready”

“Upload ~/renders/final_cut_v3.mp4 to the ‘Q3 launch’ folder and give me the share link”

Find specific feedback across projects

Search across folders, assets, and feedback at once.

“Did anyone mention the intro pacing? Show me the exact comments and links”

Triage by tag

Use tag distribution to spot the busiest themes across a folder or asset.

“Which tags are most used in the ‘Product Decisions’ folder?”

Data handling

The server only accesses data explicitly requested by the user via a tool call — no background sync, no proactive scraping
The MCP route is stateless: a fresh server is created per request and no per-request data is persisted beyond OAuth tokens and rate-limit counters
All data transmission is encrypted via HTTPS/TLS
The MCP only writes when you ask it to upload a video (from a URL or a local file); it cannot edit or delete any existing data in your Flask team
Email addresses are never exposed in MCP responses (only display name and avatar)

Support

If you run into any issues with the Flask MCP integration, reach out at hello@flask.do.

For more about how we handle your data, see our Privacy Policy.