The Model Context Protocol (MCP) is doing for AI agents what HTTP did for the web. It is a standardized interface that lets any AI model connect to any external system without custom integration code. For commerce, this means an AI agent can search products, check trust scores, and place orders through a single protocol.
GoBuy’s MCP server sits at gobuy.ai/api/mcp and exposes product intelligence tools that any MCP-compatible agent can call. This guide explains how MCP works, what GoBuy exposes, and how to integrate it.
What Is MCP?
MCP is an open-source standard originally introduced by Anthropic in late 2024. It defines a common protocol for AI applications to communicate with external servers that provide data and tools. The protocol uses JSON-RPC 2.0 over either standard I/O (for local integrations) or HTTP with Server-Sent Events (for remote integrations).
The analogy that the official documentation uses is apt: MCP is like USB-C for AI applications. Before USB-C, every device needed its own cable. Before MCP, every AI agent needed custom API integration code for every service it wanted to use.
The protocol is now supported by a broad ecosystem of clients including Claude, ChatGPT, Visual Studio Code, Cursor, and many others. If you build an MCP server, your tools are available to all of these clients without any per-client work.
Core MCP Concepts
MCP servers expose three types of capabilities:
- Resources: Read-only data sources that clients can fetch. Think of these as files the agent can read.
- Tools: Functions the agent can call with arguments. These are the primary mechanism for taking action.
- Prompts: Pre-written templates that help users accomplish specific tasks.
GoBuy’s MCP server primarily exposes tools, since product intelligence is an action-oriented capability.
GoBuy MCP Tools
GoBuy exposes three core tools through its MCP server:
search_products
Search the GoBuy product database by natural language query, category, or ASIN.
{
"tool": "search_products",
"arguments": {
"query": "wireless mechanical keyboard under $100",
"category": "electronics",
"limit": 7
}
}
Returns: List of products with name, ASIN, price, Smart Score, and trust band. Results are ranked by Smart Score, not by Amazon ranking or ad spend.
get_trust_score
Get the full trust breakdown for a specific product, including review analysis details.
{
"tool": "get_trust_score",
"arguments": {
"asin": "B0XXXXXXXX"
}
}
Returns: Smart Score (0-100), trust band, component breakdown (review authenticity, sentiment depth, seller reputation, price-to-quality, cross-platform consistency), total reviews vs. verified reviews, and flagged review percentage.
compare_products
Compare multiple products side by side on trust, quality, and price.
{
"tool": "compare_products",
"arguments": {
"asins": ["B0XXXXXXXX", "B0YYYYYYYY", "B0ZZZZZZZZ"]
}
}
Returns: Side-by-side comparison with Smart Scores, component breakdowns, price, and a recommendation based on the best trust-to-value ratio.
Integration Examples
Connecting from Claude Desktop
Add GoBuy as an MCP server in your Claude configuration:
{
"mcpServers": {
"gobuy": {
"url": "https://gobuy.ai/api/mcp",
"type": "sse"
}
}
}
Once connected, Claude can call GoBuy tools directly. You can ask Claude “Find me the best wireless headphones under $200” and it will query GoBuy’s MCP server, receive Smart Scores, and recommend products based on trust, not just Amazon rankings.
Connecting from a Python Agent
If you are building a custom agent in Python using the MCP SDK:
from mcp import ClientSession
from mcp.client.sse import sse_client
async def search_product(query: str):
async with sse_client("https://gobuy.ai/api/mcp") as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool(
"search_products",
{"query": query, "limit": 7}
)
return result
# Search for products
products = await search_product("espresso machine under $500")
Connecting from a TypeScript/Node Agent
import { Client } from "@modelcontextprotocol/sdk/client";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse";
const transport = new SSEClientTransport(
new URL("https://gobuy.ai/api/mcp")
);
const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(transport);
const result = await client.callTool({
name: "get_trust_score",
arguments: { asin: "B0XXXXXXXX" }
});
console.log(result.content);
Authentication
GoBuy’s MCP server uses two tiers of access:
No auth required: search_products and get_trust_score are open. Any agent can query product data and trust scores without authentication. This is by design. Trust information should be universally accessible.
API key required: Purchasing tools and high-rate API calls require an API key passed via the Authorization: Bearer header. API keys are available through gobuy.ai and are designed for agents that need to execute transactions, not just read data.
Why Agents Need Trust Intelligence
Without GoBuy, an AI agent shopping on Amazon is flying blind. It sees the same manipulated reviews, the same sponsored placements, and the same distorted rankings that human shoppers see. An agent that recommends a product based on fake reviews is no better than a human who falls for them.
With GoBuy’s MCP server, agents get the filtered truth. They can make recommendations based on Smart Scores that strip away manipulation and reflect genuine product quality. This is the difference between an agent that shops naively and one that shops intelligently.
Building the Agentic Commerce Stack
GoBuy’s MCP server is one piece of the agentic commerce stack. A complete agent might connect to:
- GoBuy MCP for product trust intelligence and search
- Stripe MCP for payment processing
- Amazon Product API for real-time pricing and availability
- Shipping APIs for delivery tracking
- Calendar MCP for purchase timing and reminders
Each of these is a modular capability the agent can use. The MCP protocol means they all speak the same language.
Get Started
Full API documentation, including rate limits, response schemas, and advanced usage patterns, is available at gobuy.ai/agent-docs.
Integrate our MCP at gobuy.ai/agent-docs and start building agents that shop with trust.