mcpField
S
Shade

Shade

Remote
github.com/shade-labsFiles & Storage0Updated 15w ago
Repository

About Shade

Shade MCP connects AI assistants to creative assets in a Shade workspace. It supports asset discovery and inspection as well as workspace organization, collaboration, and automation.

Key features

  1. 01Search and browse drives
  2. 02Inspect assets and transcripts
  3. 03Manage files and metadata
  4. 04Organize collections and views
  5. 05Comment and create share links
  6. 06Manage custom objects and automations

Use cases

  1. 01Find clips by visual content
  2. 02Review video summaries and preview frames
  3. 03Locate recent graded exports
  4. 04Curate assets for a review collection

MCP support

Exposes Shade workspace drives, assets, metadata, collections, comments, sharing, custom objects, and automations to MCP clients. It uses an OAuth-authenticated Streamable HTTP endpoint.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.shade.inc/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Shade MCP

Shade MCP connects AI assistants to the creative assets in your Shade workspace. It can search and browse drives, inspect assets and transcripts, manage files and metadata, curate collections and views, add comments, create share links, work with custom objects, and manage automations.

Connect

The production Streamable HTTP endpoint is:

https://mcp.shade.inc/mcp

Shade uses OAuth. Your MCP client opens Shade sign-in when you connect.

Watch the production MCP reviewer walkthrough for a concise connection, search, asset-inspection, preview, and safety demo.

Cursor

Install the Shade plugin from the Cursor Marketplace, or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "shade": {
      "url": "https://mcp.shade.inc/mcp"
    }
  }
}
Codex

The marketplace-ready Codex package is in plugins/shade and depends on the reviewed Shade app. For a direct custom connection, add this to ~/.codex/config.toml:

[mcp_servers.shade]
url = "https://mcp.shade.inc/mcp"

Then run:

codex mcp login shade
Claude

Open Settings → Connectors → Add custom connector, name it Shade, and enter https://mcp.shade.inc/mcp.

GitHub Copilot CLI
copilot mcp add --transport http shade https://mcp.shade.inc/mcp
ChatGPT

In ChatGPT settings, enable Developer mode under Connectors, create a connector named Shade, and use https://mcp.shade.inc/mcp.

Example prompts

  • “Find five clips showing a person eating pizza.”
  • “Summarize this video and show representative preview frames.”
  • “Browse the project folder and identify the latest graded exports.”
  • “Show the configured approval metadata and the value on this asset.”
  • “Create a review collection and add these selected assets.”

Security and privacy

Shade MCP only accesses workspaces and drives available to the authenticated Shade user. Mutating tools require the host's normal approval flow. See the Shade Privacy Policy, Terms of Service, and security and legal overview.

For help, visit the Shade Help Center.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.