Wishfinity MCP Plusw

🚀 +W MCP Server (Wishfinity)

+W is a universal "save for later" action in commerce. This MCP server enables AI assistants to save any product URL to a user's Wishfinity wishlist with a single click. It is compatible with Claude, ChatGPT, Gemini, LangChain, OpenAI Agents SDK, and any MCP-compatible client.

🚀 Quick Start

Option 1: Local installation (stdio transport)

Ideal for Claude Desktop, ChatGPT Desktop, Cursor, VS Code, and local development.

npm install wishfinity-mcp-plusw

Add the following to your MCP client configuration:

{
  "mcpServers": {
    "wishfinity": {
      "command": "npx",
      "args": ["wishfinity-mcp-plusw"]
    }
  }
}

Option 2: Remote endpoint (HTTP transport)

Suitable for server-side agents, LangChain production deployments, and hosted AI applications.

https://mcp.wishfinity.com/mcp

Or use the Cloudflare Workers URL:

https://wishfinity-mcp-plusw.wishfinity.workers.dev/mcp

✨ Features

When an AI recommends a product, it can present the +W Add to Wishlist option. When the user clicks the link, the product is saved to their Wishfinity account, ready for future purchase or gifting.

User: "Find me a good espresso machine under $200"

AI: Here are 3 options...
    [+W Add to Wishlist] [View on Amazon]

📦 Installation

Claude Desktop

Add the following to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "wishfinity": {
      "command": "npx",
      "args": ["wishfinity-mcp-plusw"]
    }
  }
}

ChatGPT Desktop

Once MCP support is available, add the following to your ChatGPT MCP configuration:

{
  "mcpServers": {
    "wishfinity": {
      "command": "npx",
      "args": ["wishfinity-mcp-plusw"]
    }
  }
}

Cursor

Add the following to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "wishfinity": {
      "command": "npx",
      "args": ["wishfinity-mcp-plusw"]
    }
  }
}

LangChain

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent

async def main():
    client = MultiServerMCPClient({
        "wishfinity": {
            "command": "npx",
            "args": ["wishfinity-mcp-plusw"],
            "transport": "stdio",
        }
    })
    
    tools = await client.get_tools()
    agent = create_agent("openai:gpt-4", tools)
    
    result = await agent.ainvoke({
        "messages": [{"role": "user", "content": "Find me a coffee maker and save it to my wishlist"}]
    })

For production (HTTP transport):

client = MultiServerMCPClient({
    "wishfinity": {
        "url": "https://mcp.wishfinity.com/mcp",
        "transport": "streamable_http",
    }
})

OpenAI Agents SDK

from agents import Agent, Runner
from agents.mcp import MCPServerStdio

async def main():
    async with MCPServerStdio(
        name="wishfinity",
        params={
            "command": "npx",
            "args": ["wishfinity-mcp-plusw"],
        },
    ) as server:
        agent = Agent(
            name="Shopping Assistant",
            instructions="Help users find products and save them to wishlists.",
            mcp_servers=[server],
        )
        
        result = await Runner.run(agent, "Find a good gift for a coffee lover and save it")
        print(result.final_output)

Hugging Face Agents

from huggingface_hub import Agent

agent = Agent(
    model="meta-llama/Llama-3.1-70B-Instruct",
    mcp_servers=[{
        "command": "npx",
        "args": ["wishfinity-mcp-plusw"]
    }]
)

response = agent.run("Find me running shoes under $150 and save to wishlist")

🔧 Technical Details

How it works

1. The AI calls the add_to_wishlist tool with a product URL.
2. The MCP server returns a Wishfinity link: https://wishfinity.com/add?url=...
3. The user clicks the link, logs in (only on the first time), and the product is saved.
4. The user can organize, share, or purchase the product later.

No API keys are required. Authentication occurs on Wishfinity's website when the user clicks the link.

Tool: add_to_wishlist

Input

Output

Example

// Input
{ "url": "https://amazon.com/dp/B0EXAMPLE" }

// Output
{
  "action_url": "https://wishfinity.com/add?url=https%3A%2F%2Famazon.com%2Fdp%2FB0EXAMPLE",
  "requires_user_action": true,
  "display_text": "Open to add to Wishfinity"
}

When to offer +W

AI clients should offer +W in the following situations:

• Explicit requests: Such as "save for later," "add to wishlist," "bookmark this".
• After recommending products: Proactively offer to save the shown items.
• Indecision moments: For example, "maybe later," "too expensive right now," "need to think about it".
• Gift context: Like "for my mom," "birthday gift," "perfect for my friend".

See aliases.json for the full list of trigger phrases.

Transports

📚 Documentation

• SPEC.md — Full technical specification
• INTEGRATION_GUIDE.md — How to integrate +W into your UI
• CLOUDFLARE_SETUP.md — Deploy your own HTTP endpoint
• aliases.json — Machine-readable trigger phrases

📄 License

This project is licensed under the MIT license.

Links

• Wishfinity
• MCP Protocol
• npm package
• MCP Registry

Changelog

v1.2.2 (December 24, 2025)

Critical Fix: npx execution for all developers

• Fixed main module detection to work with npx symlinks.
• Resolves the crash when running npx wishfinity-mcp-plusw.
• The package now works flawlessly for all npm installations.

v1.2.1 (December 24, 2025)

Critical Fix: MCP SDK compatibility

• Updated the @modelcontextprotocol/sdk dependency to ^1.25.0.
• Resolves server disconnection with SDK 1.25.1+.
• Compatible with the latest MCP SDK versions.

v1.2.0 (December 23, 2025)

• Added MCP prompts: save_for_later, shopping_assistant, gift_ideas.
• Added MCP resources: wishfinity://guide, wishfinity://triggers.
• Enhanced integration capabilities for AI assistants.