An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Runpod 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. Deploy and manage heavy compute workloads through chat.

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 · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through RunPod API.

  1. 01

    Stop pod

    Stops a running GPU pod immediately. Use this to halt billing on specific instances.

  2. 02

    Create pod

    Creates a new GPU pod. You provide the name, GPU type, and Docker image to get a node running.

  3. 03

    Get pod

    Retrieves specific details for a single GPU pod. Use this to check the status or configuration of a machine.

  4. 04

    List endpoints

    Lists all your serverless endpoints. This helps you audit where your containerized inference apps are routed.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through RunPod API.

  1. 05

    List gpu types

    Lists all available GPU hardware types. Use this to see what compute options are currently ready for deployment.

  2. 06

    List pods

    Lists all GPU pods in your account. This is how you see what is running, paused, or idle.

  3. 07

    List templates

    Lists your saved pod templates. Use this to quickly find pre-configured setups for new deployments.

Real work

What teams actually run

01

Rapid Prototyping

Spin up a GPU pod with a specific PyTorch image to test a new model immediately.

02

Resource Monitoring

Ask your agent to find idle pods so you can shut them down and save budget.

03

Serverless Management

Check the status of your inference endpoints to ensure your applications are routing correctly.

04

Automated Scaling

Use your agent to provision new hardware nodes as your workload demands increase.

Automate a task

Put RunPod API 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

RunPod API 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 RunPod API 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

855ms average. Fast in production.

RunPod API is checked daily against the live service.

Daily averagePeak 1111ms
Oct 3Today
Fastest day
691ms
Slowest day
1111ms
14-day trend
Improving-5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 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 RunPod API, so you can see the experience inside your AI.

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

RunPod API Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_mqfmppnjNgzd7DnF3DKymtiD5h0tXpOI6WsCj5ji/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 — RunPod API capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "runpod-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mqfmppnjNgzd7DnF3DKymtiD5h0tXpOI6WsCj5ji/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 RunPod API in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work RunPod API owners hand off.

This MCP is built for technical users who need to bridge the gap between AI-driven development and heavy GPU compute.

  • 01

    DevOps Engineers

    They hand off the repetitive tasks of provisioning and auditing workloads to their agent.

  • 02

    AI Developers

    They use the MCP to manage serverless LLM implementations using natural language.

FAQ

Questions RunPod API owners ask.

  • 01

    How do I connect my RunPod account?

    You need to generate an API Key in your RunPod settings with Read/Write permissions and then add that key to the MCP connection module.

  • 02

    Can I stop pods to save money?

    Yes. You can tell your agent to stop a specific pod by its ID to halt active billing.

  • 03

    What kind of hardware can I deploy?

    The MCP can list all available GPU types and templates, allowing you to choose the specific architecture you need for your workload.

  • 04

    Is this compatible with my existing AI capabilities?

    Yes, this MCP works with any MCP-compatible client like Claude, Cursor, or Windsurf.

  • 05

    Can I manage serverless functions?

    Yes, the MCP includes a capability to list all your registered serverless endpoints.

  • 06

    Can the AI forcefully terminate or delete critical production endpoint fleets on demand?

    No. This module safely allows the AI to only pause and manage running instances. Destructive deletion actions (like completely erasing a pod) are intentionally prohibited by the tooling design to protect your critical compute resources from unintended loss.

  • 07

    Can the AI provision large GPU arrays automatically?

    Yes. Using the create_pod capability, the AI can query the available hardware models (such as A100 or H100) and immediately launch new Docker clusters based on existing community templates, simplifying complex DevOps scaling actions significantly.

  • 08

    Will the AI know the billing state or the real-time cost of running each endpoint?

    No. The current RunPod AI module is concentrated on operational control and system orchestration, such as discovering inactive processes and booting new instances. Deep billing analytics or invoice extraction is not natively integrated in the commands exposed to the AI at this time.

Explore

More in Superpower

Suggestions

Connect RunPod API to Claude, Cursor, ChatGPT & more