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 - Editor

    1. Choose a productMCP Server
    2. Choose a workflowLocal with an editor
    3. 3Build and testFollow your tutorial

    MCP Server tutorial/Local with an editor

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

    Follow along using

    Zuplo PortalLocal with an editorLocal with an AI agent

    Turn an OpenAPI-described API into a managed MCP server. This path builds it with the Zuplo CLI and your editor.

    Zuplo allows you to instantly add a managed MCP Server to your existing API, powered by OpenAPI.

    If you're not familiar with Zuplo, it's recommended to go through Step 1 first.

    1. Create a new project

      Create a new project and start the local development server:

      TerminalCode
      npx create-zuplo-api@latest cd example-project npm run dev

      See Step 1 for a walkthrough of the create-zuplo-api prompts.

    2. Test the Get all todos route

      The default template ships with a working todo API. Open the local Route Designer at http://localhost:9100, select the Get all todos route, and click the Test button next to the Path field.

      A test dialog will open, click Test and you should see a 200 OK response with a few todos.

      This is the basic API we're going to turn into a fully functioning MCP Server.

    3. Create an MCP Server

      On your routes.oas.json file, choose Add and then Dynamic OpenAPI to MCP Server.

      Add Route

      A new route will appear. Confirm the following values:

      • Summary: enter MCP Server
      • Method: choose POST
      • Path: enter /mcp (the path can be anything, but /mcp is common)

      Click the Select Tools option for your new MCP Server endpoint.

      Select Tools

      You should see the MCP tools dialog. Check the tools from your *.oas.json files that you want to surface in your MCP Server.

      MCP Server

      Click Update Tools, then click Save at the bottom left. Congratulations, you just published your first MCP Server! It's now available locally at http://localhost:9000/mcp.

    4. Connect an MCP Client

      You can connect any MCP client that can reach your local gateway. The AI coding agent you configured in Step 1 (such as Claude Code or Cursor) is a great option — point it at your local MCP server URL:

      Code
      http://localhost:9000/mcp

      Since we didn't add authentication to our API, no credentials are required.

      Using a cloud MCP client

      Cloud clients like the OpenAI playground can't reach localhost. To use one, deploy your project first — see Step 4 — and use your deployed MCP server URL instead.

    5. Test your MCP Server

      Prompt your MCP client to:

      list out all the todos

      The client should recognize that it needs to call the todos MCP Server. Approve the tool call and you should see the todos listed 👏

    Congratulations! Now go read more about the MCP Server handler.

    Getting Started with MCP Server - PortalAgent
    On this page
    • Create a new project
    • Test the Get all todos route
    • Create an MCP Server
    • Connect an MCP Client
    • Test your MCP Server