Wishfinity +W MCP Server
Enables AI assistants to save product URLs to a user's Wishfinity wishlist. When recommending products, the AI can generate a clickable link that saves items for later purchase or gifting.
README
+W MCP Server (Wishfinity)
+W is a universal "save for later" action for commerce. This MCP server lets AI assistants save any product URL to a user's Wishfinity wishlist with one click.
Works with Claude, ChatGPT, Gemini, LangChain, OpenAI Agents SDK, and any MCP-compatible client.
What it does
When an AI recommends a product, it can offer +W Add to Wishlist. The user clicks the link, and the product is saved to their Wishfinity account — ready for later purchase or gifting.
User: "Find me a good espresso machine under $200"
AI: Here are 3 options...
[+W Add to Wishlist] [View on Amazon]
Quick start
Option 1: Local installation (stdio transport)
Best for Claude Desktop, ChatGPT Desktop, Cursor, VS Code, and local development.
npm install wishfinity-mcp-plusw
Add to your MCP client configuration:
{
"mcpServers": {
"wishfinity": {
"command": "npx",
"args": ["wishfinity-mcp-plusw"]
}
}
}
Option 2: Remote endpoint (HTTP transport)
Best 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
Platform Setup Guides
Claude Desktop
Add 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
When MCP support is available, add to your ChatGPT MCP configuration:
{
"mcpServers": {
"wishfinity": {
"command": "npx",
"args": ["wishfinity-mcp-plusw"]
}
}
}
Cursor
Add 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")
How it works
- AI calls the
add_to_wishlisttool with a product URL - MCP server returns a Wishfinity link:
https://wishfinity.com/add?url=... - User clicks the link → logs in (first time only) → product is saved
- User can organize, share, or purchase later
No API keys required. Authentication happens on Wishfinity's website when the user clicks the link.
Tool: add_to_wishlist
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
url |
string | Yes | Product page URL |
Output
| Field | Type | Description |
|---|---|---|
action_url |
string | Wishfinity link to open in browser |
requires_user_action |
boolean | Always true (user must click) |
display_text |
string | Suggested button label |
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 when:
- Explicit requests: "save for later," "add to wishlist," "bookmark this"
- After recommending products: Proactively offer to save shown items
- Indecision moments: "maybe later," "too expensive right now," "need to think about it"
- Gift context: "for my mom," "birthday gift," "perfect for my friend"
See aliases.json for the full list of trigger phrases.
Transports
| Transport | Use Case | Endpoint |
|---|---|---|
| stdio | Local clients (Claude Desktop, Cursor, etc.) | npx wishfinity-mcp-plusw |
| HTTP | Remote/server-side agents | https://mcp.wishfinity.com/mcp |
Button kit
The /button-kit folder contains optional UI assets (SVG icon, HTML/CSS snippets) if you want a consistent +W button appearance.
CDN URLs:
- Small:
https://cdn.jsdelivr.net/npm/wishfinity-mcp-plusw@latest/button-kit/Wishfinity-Button-Small.svg - Medium:
https://cdn.jsdelivr.net/npm/wishfinity-mcp-plusw@latest/button-kit/Wishfinity-Button-Medium.svg - Large:
https://cdn.jsdelivr.net/npm/wishfinity-mcp-plusw@latest/button-kit/Wishfinity-Button-Large.svg
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
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.