How to Use the Artsy MCP in Claude Code

Q: How do I get a list of all art genes from Artsy using Claude Code in a script?

In your shell script, you'd run claude mcp run artsy-mcp listgenes. This will output a JSON array of all genes, like 'Abstract Expressionism' or 'Pop Art', to stdout, which you can then pipe to other commands.

Q: Can I search for an artist from the command line with the Artsy and Claude Code integration?

Yes. The command would be something like claude mcp run artsy-mcp searchartsy --params '{"query": "picasso"}'. You'll get a structured JSON response right in your terminal.

Q: Does the server log my Claude Code commands for Artsy?

No. All operations are stateless. The server executes your listfairs or getartistdetails request and returns a response without logging the query itself.

Pipe the entire Artsy database into your shell scripts and CI/CD jobs. Headless, fast, and built for automation with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Artsy MCP to Claude Code

Create your Vinkius account to connect Artsy 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 Artsy with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Art Data in Your Terminal

This brings the Artsy database right into your shell. Use Claude Code to run `search_artsy` and pipe the JSON output directly to `jq` for filtering. It's perfect for building automated reports or backend scripts. Imagine a cron job that runs every morning: `claude mcp run artsy-mcp list_shows --params '{"location": "london", "status": "upcoming"}' | notify-slack`. You can build powerful, headless workflows that monitor the art world without ever leaving the command line.

Use Artsy Data in Your CI Pipelines

Add this MCP Server to your CI/CD environment. You can write a GitHub Action that uses Claude Code to run `list_artworks` and validate data integrity before a deployment. Or, use it to generate a static sitemap based on the latest artists. Because it's just a CLI command, integration is trivial. You can use tools like `get_artist_details` to enrich build-time data or run checks against your database content, all within your existing pipeline.

Headless Data Extraction with this MCP Server

Forget web scraping. Connect Claude Code to the Artsy server for clean, structured data extraction. You can pull down entire lists of art fairs with `list_fairs` or get details on thousands of pieces using `get_artwork_details` in a simple script. The output is clean JSON, ready for any data processing task. It's the most direct way to get art market data for analysis, database seeding, or any backend process. Just one command connects you.

Setup guide

Set up Artsy 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 artsy-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http artsy-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 Artsy 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": {
    "artsy-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 Artsy. 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 Artsy 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 Artsy MCP in Claude Code

In your shell script, you'd run `claude mcp run artsy-mcp list_genes`. This will output a JSON array of all genes, like 'Abstract Expressionism' or 'Pop Art', to stdout, which you can then pipe to other commands.

Yes. The command would be something like `claude mcp run artsy-mcp search_artsy --params '{"query": "picasso"}'`. You'll get a structured JSON response right in your terminal.

Authentication and discovery are handled for you. You add the server once, and Claude Code manages the token. It also provides a consistent interface for all tools, so you don't have to fuss with different endpoints or headers for each operation.

No. All operations are stateless. The server executes your `list_fairs` or `get_artist_details` request and returns a response without logging the query itself.

The connection is secure and minimal. The Vinkius MCP server only receives the tool name and parameters for your query, like an artist's name or a search term. It runs in an ephemeral container, so no data about your queries or your environment is ever stored.

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