Before you begin, make sure you have an OpenSea API key. See Getting Started for instructions.

Claude Desktop

Claude Desktop supports MCP servers natively.

1. Open your configuration file

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Create the file if it doesn't exist.

2. Add the OpenSea MCP server

{
  "mcpServers": {
    "OpenSea": {
      "url": "https://mcp.opensea.io/mcp",
      "headers": {
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your OpenSea API key.

3. Restart Claude Desktop

Quit and reopen the app. You should see a hammer icon in the chat input, indicating MCP tools are available. Click it to confirm the OpenSea tools are listed.

Cursor

Cursor supports MCP servers for use in its AI features.

1. Open MCP settings

Go to Cursor Settings > MCP > Add new global MCP server, or edit the file directly:

Project-level: .cursor/mcp.json in your project root
Global: ~/.cursor/mcp.json

2. Add the OpenSea MCP server

{
  "mcpServers": {
    "OpenSea": {
      "url": "https://mcp.opensea.io/mcp",
      "headers": {
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your OpenSea API key.

3. Verify the connection

Open Cursor Settings > MCP. The OpenSea server should show a green status indicator. You can now reference OpenSea data in Composer and Agent mode.

VS Code (GitHub Copilot)

GitHub Copilot in VS Code supports MCP servers in Agent mode.

1. Enable MCP support

Open VS Code Settings (Cmd+, / Ctrl+,) and search for mcp. Ensure Chat > MCP: Enabled is checked.

2. Add the OpenSea MCP server

Open your VS Code settings.json (User or Workspace) and add:

{
  "mcp": {
    "servers": {
      "OpenSea": {
        "type": "http",
        "url": "https://mcp.opensea.io/mcp",
        "headers": {
          "X-API-KEY": "YOUR_API_KEY"
        }
      }
    }
  }
}

Replace YOUR_API_KEY with your OpenSea API key.

3. Use in Copilot Chat

Open Copilot Chat (Ctrl+Shift+I / Cmd+Shift+I), switch to Agent mode, and click the tools icon to confirm the OpenSea tools are available.

Windsurf

Windsurf supports MCP servers for its Cascade AI assistant.

1. Open MCP configuration

Go to Windsurf Settings > Cascade > MCP, or edit the file directly at ~/.codeium/windsurf/mcp_config.json.

2. Add the OpenSea MCP server

{
  "mcpServers": {
    "OpenSea": {
      "serverUrl": "https://mcp.opensea.io/mcp",
      "headers": {
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your OpenSea API key.

3. Verify the connection

Return to the MCP settings page. The OpenSea server should show as connected. You can now use OpenSea data in Cascade conversations.

ChatGPT

OpenSea MCP is available as a ChatGPT plugin via the OpenAI Apps SDK integration.

No manual configuration is required. Search for OpenSea in the ChatGPT plugin store and enable it. The plugin uses the same MCP tools described in the MCP Overview.

Custom Applications

You can integrate OpenSea MCP into your own applications using any MCP-compatible SDK.

Vercel AI SDK (Next.js)

The Vercel AI SDK provides first-class MCP support. See the full starter project at opensea-mcp-next-sample.

import { experimental_createMCPClient as createMCPClient } from "ai";

const mcpClient = await createMCPClient({
  transport: {
    type: "sse",
    url: "https://mcp.opensea.io/sse",
    headers: {
      "X-API-KEY": process.env.OPENSEA_API_KEY,
    },
  },
});

const tools = await mcpClient.tools();

Python (mcp SDK)

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async with streamablehttp_client(
    "https://mcp.opensea.io/mcp",
    headers={"X-API-KEY": "YOUR_API_KEY"},
) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

TypeScript (mcp SDK)

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const transport = new StreamableHTTPClientTransport(
  new URL("https://mcp.opensea.io/mcp"),
  { requestInit: { headers: { "X-API-KEY": "YOUR_API_KEY" } } }
);

const client = new Client({ name: "my-app", version: "1.0.0" });
await client.connect(transport);

const { tools } = await client.listTools();

Authentication

All custom integrations authenticate with the X-API-KEY header. If your HTTP client does not support custom headers, you can pass the API key in the URL path instead:

https://mcp.opensea.io/YOUR_API_KEY/mcp
https://mcp.opensea.io/YOUR_API_KEY/sse

🔒
Prefer the header-based approach when possible. Avoid embedding API keys in URLs in client-side code where they may be visible in browser network logs.