An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Apidog to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your agent the full context of your API design.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 5 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 5 available through Apidog.

  1. 01

    Get endpoint

    Fetch the complete schema of a single API endpoint

  2. 02

    List endpoints

    List all API endpoints defined within a specific Apidog project

  3. 03

    List projects

    List all API projects in the connected Apidog organization

Capability set02 / 02

04-05

2 capabilities in this set.

Part of 5 available through Apidog.

  1. 04

    List schemas

    List all data model schemas (DTOs, entities) defined in an Apidog project

  2. 05

    Export openapi

    Export the full OpenAPI 3.0 specification of an Apidog project as JSON

Real work

What teams actually run

01

Scaffolding a new service

You ask the AI to export the OpenAPI spec for the entire project. The AI then uses that context to generate the initial boilerplate code for all 42 endpoints.

02

Writing integration tests

The QA team asks the AI to inspect a specific endpoint's schema and generate the expected response payload JSON for the test case.

03

Client-side type generation

The frontend engineer asks the AI to look at a specific endpoint's response schema and output the exact TypeScript interface needed for the client.

04

API discovery

You ask the AI to list all projects in the organization, helping you quickly identify which API contract you need to work with.

Automate a task

Put Apidog to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Apidog works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Apidog to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

852ms average. Fast in production.

Apidog is checked daily against the live service.

Daily averagePeak 1100ms
Oct 3Today
Fastest day
718ms
Slowest day
1100ms
14-day trend
Stable+2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 5 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Apidog, so you can see the experience inside your AI.

It does not authenticate your account with Apidog. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Apidog Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_1gfzKqa8BKdlksvlirUta1L3JF2RLj6gA89JA1li/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Apidog capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "apidog-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_1gfzKqa8BKdlksvlirUta1L3JF2RLj6gA89JA1li/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Apidog in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Apidog owners hand off.

This MCP is essential for developers who need their AI agent to understand complex API contracts. Backend engineers use it to scaffold controllers or unit tests. Frontend engineers rely on it to generate client-side types. QA teams use it to automatically fetch expected response payloads for integration testing.

  • 01

    Backend Developers

    Quickly review endpoints or export a full OpenAPI spec so the AI can safely scaffold controllers or unit tests.

  • 02

    Frontend Engineers

    Ask the AI to inspect an Apidog endpoint schema and generate the corresponding TypeScript interfaces or API service layers.

  • 03

    QA Automation Teams

    Fetch expected response payloads automatically to construct robust integration tests.

FAQ

Questions Apidog owners ask.

  • 01

    What kind of data does this MCP expose?

    It exposes your entire API contract defined in Apidog. This includes a list of projects, all defined endpoints, reusable data models (schemas), and the full OpenAPI 3.0 specification.

  • 02

    Can I use this MCP to generate code?

    Yes. By providing the schema, the AI agent can generate code like TypeScript interfaces or scaffold controllers and unit tests based on your defined API contracts.

  • 03

    Does this require me to open Apidog?

    No. You connect your Apidog API Access Token to the MCP. Your AI client handles all the interaction, pulling the data directly into your chat environment.

  • 04

    What is the difference between listing endpoints and getting an endpoint?

    Listing endpoints gives you a directory of all available routes in a project. Getting an endpoint fetches the complete, detailed schema for one specific route, including its methods and body requirements.

  • 05

    Is the OpenAPI export usable for testing?

    Yes. The export provides the full OpenAPI 3.0 JSON specification, which is the standard format for generating robust integration and unit tests.

  • 06

    Can I import a complete OpenAPI spec into an AI chat session?

    Yes. Instruct the agent to run the export_openapi capability. It downloads the JSON metadata and safely passes it into your context. Given its size, the agent can use this massive reference guide to rapidly write tests, endpoints, or data models perfectly mimicking your production systems.

  • 07

    How can I check the payload requirements for a single specific route?

    If you know the general area of the project, use list_endpoints to verify the ID. Then query get_endpoint. It brings back the specific HTTP verbs, query arguments, path definitions, and expected JSON body. letting your agent craft exact functional requests to external systems.

  • 08

    Will my Apidog tokens expire?

    When generating your Personal Access Token in Apidog, you dictate the validity duration (e.g. 30 days, 1 year or never expire). If you choose a finite span, you will need to come back, generate a new token and insert it once more to reconnect the MCP server successfully.

Explore

More in Productivity

Suggestions

Connect Apidog to Claude, Cursor, ChatGPT & more