MCP For Claude Marketplace
RunPod

RunPod MCP Connector for Claude

A+

Integrate your AI securely to RunPod to cleanly quickly provision scalable GPU pods, manage active instances, and inspect serverless endpoints and custom templates natively.

7 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your AI directly to RunPod, the leading cloud infrastructure provider for on-demand GPU computing and serverless execution. Empower your conversational agent to act as a highly proficient DevOp engineer, managing advanced computational workloads, exploring deployment options, and spinning up new hardware instances.

What you can do

  • Manage Pods On-Demand — Effortlessly identify running and paused GPU machines across your cloud account (list_pods, get_pod). Halt specific billable instances to control costs securely (stop_pod).
  • Provision GPU Workloads — Find verified templates or specific GPU architectures ready for deployment (list_templates, list_gpu_types), and create entirely new hardware nodes immediately directly from chat (create_pod).
  • Audit Serverless Environments — Review all registered endpoints routing your containerized inference applications (list_endpoints).

How it works

  1. Successfully enable the RunPod orchestration integration inside your core interface.
  2. Sign into your RunPod cloud console and navigate to 'Settings' > 'API Keys'.
  3. Generate a new API Key with Read/Write permissions and insert this secret inside the secure connection module below.
  4. Interact seamlessly: "List all active GPU pods and point out any that are sitting idle without active usage."

Who is this for?

  • DevOps Engineers — Instantly provision and audit heavy workloads directly from chat interfaces without toggling through web dashboards.
  • AI Developers — Manage high-power serverless LLM implementations organically via organic language requests.
gpu-computingserverless-deploymentcloud-instancesmachine-learning-opscontainer-orchestrationinfrastructure-as-code

7 tools expose this connector's capabilities to your AI agent.

stop_pod

Stops a running GPU pod

create_pod

Specify name, GPU type, and Docker image. Creates a new GPU pod

get_pod

Retrieves details for a specific GPU pod

list_endpoints

Lists all serverless endpoints

list_gpu_types

Lists available GPU hardware types

list_pods

Lists all GPU pods in the account

list_templates

Lists saved pod templates

See how to talk to your AI agent using RunPod.

Show me our stopped GPU pods.

I successfully verified the RunPod platform logs. You have 2 pods currently in a paused stopped status in your configured account.

Check what GPU templates are available to deploy a new Llama-3 inference instance.

I have loaded the RunPod catalog template arrays. There are several pre-built images with focused PyTorch and vLLM installations tuned perfectly for Llama-3 text deployments. Would you like me to provision one specific GPU?

Pause pod with ID 'pod_xyz_980' immediately to prevent recurring costs throughout the evening.

Pod 'pod_xyz_980' has been carefully stopped securely. Active hourly billing operations to compute cycles for this specific cloud target are halted.

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.

Related Connectors

Design Pickle

Design Pickle MCP

10 tools Official

Equip your AI agent to manage graphic design requests, track brand profiles, and monitor your production queue via the Design Pickle API.

A+ View details →
GitHub

GitHub MCP

12 tools

Manage repositories, pull requests, issues, and CI/CD workflows on the world largest developer collaboration platform.

A+ View details →
Zakeke

Zakeke MCP

9 tools Official

Manage customized product designs, 3D configurations, and orders via Zakeke.

A+ View details →
Kaggle Market Intelligence

Kaggle Market Intelligence MCP

10 tools Official

Transform Kaggle into your primary data science engine. Deploy autonomous agents to intercept trending datasets, track competition discussions, and engage data scientists in real-time.

A+ View details →