Koskamo

Berrys MCP

Berrys MCP connects AI agents to the Berrys creative infrastructure via the Model Context Protocol. It allows users to plan, approve, and execute paid creative runs within their existing AI agents, keeping all results on an editable canvas. The server supports generating brand-consistent marketing content such as ad variations, catalogue shots, UGC-style content, graphic posters, and short-form videos.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Berrys MCP logo, by Berrys AI Labs Pte LtdCommunity listingStreamable HTTPOAuth sign-inEndpoint checked 2026-11-02Published by Berrys AI Labs Pte Ltd
MCP endpoint (Streamable HTTP)
https://app.berrys.io/api/mcp
Vendor documentation

What you can do with it

  • Generate brand-consistent ad variations
  • Create catalogue and lifestyle shots
  • Produce UGC-style content and graphic posters
  • Create campaign shots and short-form videos

Source and maintenance

Community listingRegistry 0.3.0

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
456 ms
95th percentile latency
456 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 456 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http berrys-mcp https://app.berrys.io/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add berrys-mcp --url https://app.berrys.io/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable berrys-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "berrys-mcp": {
      "url": "https://app.berrys.io/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "berrys-mcp": {
      "type": "streamableHttp",
      "url": "https://app.berrys.io/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start berrys-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "berrys-mcp": {
      "type": "http",
      "url": "https://app.berrys.io/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http berrys-mcp https://app.berrys.io/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "berrys-mcp": {
      "url": "https://app.berrys.io/api/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "berrys-mcp": {
      "serverUrl": "https://app.berrys.io/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Berrys MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.