ZuploZuplo
LoginStart for Free
  • Documentation
  • API Reference
Getting Started
Concepts
API Management
AI Gateway
MCP Gateway
MCP Server
    Overview
    Getting Started
      ToolsPromptsResourcesTestingTroubleshootingGraphQLCustom ToolsOpenAI Apps SDK
      Guides
      Configuration Migration Guide
    Developer Portal
    Development
    Deploying & Source Control
    Analytics
    Observability
    Networking & Infrastructure
    Account Management
    Programming API
    Build with AI
    Zuplo CLI
    Migration Guides
    Platform LimitsVersion Support PolicySecuritySupportTrust & ComplianceChangelog
    powered by Zuplo
    MCP Server

    Getting Started with MCP Server

    1. Choose a productMCP Server
    2. 2Choose a workflowHow you want to work
    3. 3Build and testFollow your tutorial

    An MCP server makes API operations available as tools for AI assistants through the Model Context Protocol (MCP). This tutorial adds an MCP interface to a sample Todo API using its OpenAPI document.

    Choose a workflow to create the server, select its tools, and test a tool call. The sample API is provided. Use an MCP client, such as MCP Inspector, to test the result. For the local guides, use a client that can reach your machine.

    Choose a workflow to start

    Pick one of these three options to open your tutorial. You can switch workflows later in the guide.

    Zuplo PortalConfigure your project in the browser with the visual Route Designer and built-in testing tools.What you'll needa browser and a free Zuplo accountUse the PortalLocal with an editorCreate a project with the Zuplo CLI, edit its files, and test changes on your machine.What you'll needNode.js 24+, a terminal, and your editorUse an editorLocal with an AI agentUse a guided prompt with Claude Code, Cursor, or Codex, then review and test the changes.What you'll needNode.js 24+ and an AI coding agentUse an AI agent

    What you'll build

    About 15 min for the tutorial

    Expose a sample Todo API as an MCP server and test its tools with an MCP client.

    • Create a project with a sample API
    • Choose which API operations become tools
    • Connect an MCP client and call a tool