What is MCP?

Model Context Protocol (MCP) is an open standard developed by Anthropic, the company behind Claude. While it may sound technical, but the core idea is simple: give AI agents a consistent way to connect with tools, services, and data — no matter where they live or how they’re built.

MCP is a big leap forward in how AI agents operate. Instead of just answering questions, agents can now perform useful, multi-step tasks — like retrieving data, summarizing documents, or saving content to a file.

Why it matters?

Before MCP, each of those actions required a unique API, custom logic, and developer time to glue it all together.

With MCP, it’s plug-and-play. Agents can send structured requests to any MCP-compatible tool, get results back in real time, and even chain multiple tools together — without needing to know the specifics ahead of time.

In short: MCP replaces one-off hacks with a unified, real-time protocol built for autonomous agents.

MCP Servers

An MCP server is like a smart adapter for a tool or app. It knows how to take a request from an AI (like “Get today’s sales report”) and translate it into the commands that tool understands.

For example:

• A GitHub MCP server might turn “list my open pull requests” into a GitHub API call.
• A File MCP server might take “save this summary as a text file” and write it to your desktop.
• A YouTube MCP server could transcribe video links on demand.

MCP servers also:

• Tell the AI what they can do (tool discovery)
• Interpret and run commands
• Format results the AI can understand
• Handle errors and give meaningful feedback

MCP Architecture

MCP Clients

On the other side, an MCP client lives inside the AI assistant or app (like Infosys Equinox MCPs). When the AI wants to use a tool, it goes through this client to talk to the matching server.

Why does MCP Matter?

Depending on where you sit in the ecosystem, MCP can have a range of benefits.

Developers: MCP reduces development time and complexity when building, or integrating with, an AI application or agent.

AI applications or agents: MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.

End-users: MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.

How it Works?

This server allows your service or agent to:

• Perform specific related actions (e.g., catalog management, promotion management, storefront operations etc.)
• Respond to user/system triggers
• Integrate with other MCPs for orchestrated workflows

 Example Flow

• A request is initiated by the user or system.
• The MCP server processes the request and returns structured data.
• The frontend or downstream service consumes the response. 

Step 1: Equinox MCP Servers Access Request

Infosys Equinox MCP servers support service-specific tasks by providing on-demand access to MCP tools. Use the corresponding cloud environment URLs to explore, test, and validate the features of each MCP server.

Step 2: Connection Details

To enable communication between AI agents and backend services, each MCP server is exposed via a standardized endpoint using the following URL format:

Base URL: https://<Domain>/<mcp-name>/mcp

For example, https://eq-cloud-mcpgw.equinox.shop/catalog/mcp

Following are the examples for Catalog MCP. Taking reference, you can connect any other MCPs.

For VSCode

Use the following request format to call the MCP tools in VSCode.

Note: Add the following configuration to .vscode/mcp.json:

{
    "servers": {
        "catalog": {
            "type": "http",
            "url": "https://eq-cloud-mcpgw.equinox.shop/catalog/mcp"
        }
    }
}

Claude Desktop

Use the following request format to call the MCP tools in Claude.

Note: Add the following configuration to claude_desktop_config.json

{
    "mcpServers": {
        "catalog": {
            "url": "https://eq-cloud-mcpgw.equinox.shop/catalog/mcp"
        }
    }
}

Similarly, you can host MCP as per instructions from other tools.

Cursor

Use the following request format to call the MCP tools in Cursor.

Note: Add the following configuration ~/.cursor/mcp.json

{
    "mcpServers": {
        "catalog": {
            "url": "https://eq-cloud-mcpgw.equinox.shop/catalog/mcp"
        }
    }
}

Step 3: Accessing the MCP Tool Request Format

{
  "method": "tools/call",
  "params": {
    "name": "tool name",
    "arguments": {
      "arg1": "arg1 value",
      "arg2": "arg2 value",
      "x-auth-token": ""
    }
  }
}

List of MCP Server URLs

The table below outlines all MCP service names along with their corresponding MCP server URLs:

Revision History

2026-01-22 | JP – Updated Cloud URL details
2025-09-23 | JP – Page created and content added