Schedule a demo

NEW – Now in Claude, ChatGPT, and Cursor

Your agents can now do more
than just looking for your files.

Playbook speaks the Model Context Protocol (MCP), so your AI agents can handle tedious tasks without asking you where things are. Search, tag, version, organize, share.

Start for free See MCP examples

Quick setup

Connect your workspace to
Claude, ChatGPT, or Cursor

Pick the tool you already work in and authorize once.

Read MCP guide See API reference

  1. Open Playbook in Claude

    It is listed in Claude's connector directory. One connection covers Claude on the web, desktop, and mobile.

    Open in Claude

  2. Connect it there

    Connect it from its directory page. To add it by hand instead, paste this URL as a custom connector.

    https://mcp.playbook.com/mcp

  3. Sign in and start

    Authorize Playbook once, then ask Claude to find, tag, or organize anything in your library.

    Start for free

How does Playbook MCP work?

  1. Post house just dropped the Scene 4 delivery into the workspace. Help me sort clips into Scenes selections, stills into Images, anything branded into Collateral.

  2. Reading 16 new assets against the project boards...

  3. Eight clips into Scene selections, three stills into Images, five into Collateral. The two re-renders of shots went in as versions. Nothing overwritten.

A new board of hero shots with a view-only share link

Tools

Endless possibilities
once it's connected

Stop describing where a file lives. Ask for the file.

Find it by what it looks like

Describe the shot and get matches, no tags required. Overexposed, shot from below, too much orange. This is the one your agent has that a filter panel doesn't.
ai_search

Filter across everything at once

Tags, status, custom fields, file type, uploader, all combined in a single query. The kind of question that takes a person six passes through a grid.
search_assets

Read the whole library, not a page of it

Walks the full board tree in one pass, nested boards included. This is what lets an agent answer questions about four thousand files instead of the forty on screen.
list_assets

Write the metadata back

Titles, tags, custom fields, board placement. Point at a product sheet, match SKUs, and the fields land on every asset that matched.
update_asset

Change state on a thousand assets at once

One call, across boards, approved or not. The afternoon of clicking after a review round, collapsed.
set_asset_approval

Bring a hundred files in per call

Give it URLs and it fetches, routes to the right board, and applies titles and tags on the way in. A catalog arrives structured instead of arriving as a pile.
upload_from_urls

Search and read

  • ai_search Find assets by what they look like.
  • search_assets Filter by tag, status, field, or type.
  • list_assets Read a whole library or board tree.
  • get_assets Full detail for up to a hundred assets.
  • get_asset_previews Render assets at the size you choose.

Boards

  • list_boards The board tree, at any depth.
  • list_board_children The child boards under one board.
  • get_board A board's title, description, and count.
  • create_board A new board, nested where you want it.
  • update_board Rename a board or move it elsewhere.
  • copy_assets Copy assets into another board.
  • move_assets Move assets to a different board.

Metadata

  • update_asset Write titles, tags, and fields onto an asset.
  • update_asset_status Set the status label on an asset.
  • change_asset_tags Add and remove tags, nothing else.
  • set_asset_approval Approve up to a thousand assets at once.
  • list_custom_fields Every field in the workspace and its options.
  • create_custom_field A new field and its options.

Versions

  • create_asset_version Add a new version of the same asset.
  • list_asset_versions The full version history, newest first.
  • revert_asset Roll an asset back to an earlier version.

Sharing

  • share_board A link anyone can open, password optional.
  • publish_board A public page, with download controls.
  • asset_permalinks Add, read, or revoke permanent public URLs.

Comments and notes

  • get_comments Read the thread on an asset or board.
  • create_comment Post a comment.
  • create_note A sticky note, for a brief or a caption.

Uploads

  • upload_from_urls Bring in a hundred files per call, tagged.

Workspace

  • list_organizations Which workspaces the account can reach.
  • list_members Who's in the workspace.

Destructive

  • delete_asset Remove an asset.
  • delete_board Remove a board and everything in it.
  • delete_custom_field Remove a field and all its options.

Examples

Ready to give it a try
with your own assets?

Give me a tour of our workspace, then suggested how to structure it better. What should be organized by boards vs tags?

What you have and where it's piled up, followed by a proposed board structure.

Frequently asked questions

MCP (the Model Context Protocol) is an open standard for connecting AI assistants to outside tools and data. An app publishes an MCP server, and any MCP client can use it. Playbook publishes one, so an assistant can work with your workspace directly instead of you copying files into a chat.

Any client that speaks MCP. The steps above cover Claude, ChatGPT, Cursor, Claude Code and Codex because those are the ones teams ask for most, but the same connector URL works anywhere else.

It connects as you and works inside your account's permissions: it reaches the boards and assets you can already reach, and nothing that hasn't been shared with you. It can also make changes, the same ones you can make yourself. Tagging, filing, versioning, approving, creating boards, sharing, and bringing in files from a URL.

Deleting is a soft delete: anything removed goes to your Playbook trash and can be restored. The assistant is also instructed to confirm with you before deleting anything. On plans with version history, replacing a file keeps the original as a version you can roll back to.

Yes. One connection reaches every workspace your account belongs to, and the assistant works in whichever one you name. If you don't say, it will ask.

No. Playbook does not use your assets to train models. Once an assistant is connected, what it does with the files it retrieves is governed by that tool's own data policy.

All of them, starting with Free. MCP requests count toward your plan's monthly API calls: 1K on Free, 20K on Pro, 200K on Team, 5M on Business. See the pricing page for the full breakdown.

MCP is for the assistant: it discovers what Playbook can do and calls it on your behalf, in conversation. The REST API is for software you write. Both reach the same workspace, and the developer docs cover the API.

Wherever you work,
Playbook library is already there.

Start for free Read the docs