Run your label
from Claude.
Labelflow is building a Model Context Protocol server that will expose your catalog, communications, deliverables, and analytics to the AI client you already work in. Operators will be able to create releases, check what's blocking, and send onboarding emails directly from inside the conversation. Same software, same standards, driven from the AI you already work in.
The release-ops layer shouldn't only live behind a UI.
Most label operators already keep an AI client open next to their inbox. Claude, ChatGPT, Cursor. They write replies in it, summarize emails, sketch out plans for the week. Then they switch tabs to do the actual work, which usually means clicking around five tools to find the thing they were just thinking about.
Model Context Protocol changes the shape of that. An AI client that speaks MCP can call tools directly, see live data from your systems, and execute real actions on your behalf. Labelflow is building an MCP server so the AI you already use will become a working surface on top of your label, not a side panel to copy notes into.
Twenty-one tools, two surfaces.
The MCP server exposes eleven read tools and ten write tools at launch. Read tools let the AI pull live state out of your workspace; write tools let it act, with the same permission rules as the operator app.
Catalog & releases
List releases, get a specific release with tracks and metadata, check status. Create new releases, transition them through the pipeline, attach tracks. The catalog operations your roadmap actually runs on.
Artists & contacts
List artists, get an artist's full profile and history, search contacts by role. Create new artists at signing, update contact info as it changes. The roster surface mirrored from the operator app.
Communications
Search threads by artist or release, draft a new communication using your label's voice, send it for approval. The full Communications Engine, callable from the AI client.
Deliverables & analytics
List what's outstanding, what's blocking, what was missed. Read analytics summaries for any release or for the whole catalog. The dashboards that drive the weekly review, queryable in conversation.
The AI you already use becomes a label OS.
A few of the things you'll be able to ask once MCP ships, written the way operators actually phrase them:
OAuth or personal access tokens. Both shipped.
Two ways in, depending on setup. OAuth for the standard install path: click connect inside your AI client, sign in to Labelflow, scoped consent, done. Personal access tokens for power users, scripts, and clients that prefer header-based auth. Both go through the same permission model as the operator app: workspace-scoped, role-aware, fully auditable.
All actions logged. Every read and write tool call leaves a trail in your workspace activity log, attributed to the operator and the client. You see what the AI did, exactly when, with what arguments.
What MCP won't do.
Same AI policy as the rest of Labelflow. The MCP server inherits every restriction, not just the convenient ones.
No predictive A&R scoring.
Even via MCP, no "this artist is about to break" forecasts. AI helps you read what exists; A&R calls stay with you.
No bulk sending without approval.
Write tools can draft and queue. Final send still goes through the operator's approval, by default. Auto-send is opt-in per template, just like in the operator app.
No third-party model training.
Your workspace data, your AI client, your decision. Labelflow doesn't sell aggregated MCP traffic to model labs. AI policy applies end-to-end.
No silent destructive actions.
Deletes, status transitions, irreversible moves require explicit confirmation by default. The AI can't quietly empty a release pipeline because the prompt was ambiguous.
Operators who already think in AI clients.
If you keep Claude open all day, work in Cursor, or run your label through ChatGPT prompts and copy-paste rituals, MCP is the version of Labelflow that fits how you already work. If you mostly use the operator app and prefer it that way, MCP changes nothing for you. It's a parallel surface, not a replacement.
Bundled with all three tiers (Solo, Label, Studio). No add-on cost. See pricing →
Coming Q3 2026.
Shipping alongside paid plans in Q3 2026. Not part of the current private beta: we're scoping MCP carefully against the AI policy first, and against real operator workflows once the workspace foundation it sits on is stable. See the full roadmap →
An AI-native label OS, coming Q3.
Beta is invite-only. MCP isn't part of the current private beta. It ships alongside paid plans in Q3 2026; the workspace foundation MCP will sit on is in private beta now. Get on the list and you'll be among the first to plug your AI client in when it ships.
Request beta accessMade for the music.