How to Use the Canto MCP in Claude Code

Q: How do I add Canto to Claude Code?

Run the connection command in your terminal: claude mcp add --transport http canto -- . Make sure all flags come before the server name.

Pipe Canto asset data directly into your terminal. Let Claude Code manage metadata, sync folders, and purge files from the command line.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Canto MCP to Claude Code

Create your Vinkius account to connect Canto to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Canto with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless asset search and retrieval

Terminal dwellers do not want to open a browser to find a Canto image ID. Claude Code handles this via standard input. You type a prompt, and the CLI queries the vault using `global_asset_search`. The agent pulls the explicit payload IDs and can immediately pipe them into another tool. If you need the actual file properties, it runs `get_image_metadata` and outputs the JSON schema right to your standard output.

CI/CD syncing via the Canto MCP Server

Keeping your repository media aligned with your creative team's output is a manual nightmare. You can automate this by running Claude Code in a GitHub Action. The agent checks the remote state on a cron schedule. It enumerates the active instances using `list_canto_albums` and compares them against your local build directory. If it finds missing assets, it triggers `get_album_assets` to fetch the new payload IDs and updates your staging environment.

Scripted metadata patching and deletion

Bulk updating Canto asset tags requires programmatic access. Instead of writing a custom Python script, you just ask the CLI to do it. The agent identifies the target files using `list_canto_folders`. It then iterates through the list, firing `patch_image_metadata` to rewrite the properties. For files marked for deletion, it executes `wipe_media_asset` to vaporize the app nodes. One terminal command replaces hundreds of manual API calls.

Setup guide

Set up Canto MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see canto-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Canto transactions." It will automatically discover and invoke the available Canto tools.

Terminal

claude mcp add --transport http canto-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Canto MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "canto-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Canto. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Canto now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Canto MCP in Claude Code

Run the connection command in your terminal: `claude mcp add --transport http canto -- `. Make sure all flags come before the server name.

Yes. You can pipe a text file containing search terms into the CLI. The agent will read the file and execute the search tool for each line.

You likely put the transport flags in the wrong order during setup. Check your `~/.claude.json` file. The MCP server configuration must use the HTTP transport to hit the Vinkius endpoint.

The CLI can loop the wipe command. You pass it a list of IDs, and it will iterate through them. Keep in mind that dropping database bytes is irreversible.

Everything runs inside a V8 Isolate MCP Sandbox. Your image schemas, search queries, and folder names are processed in memory. The environment is destroyed as soon as the terminal command exits.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript