# RunPod — how to use (mcp.ai)

Connect your RunPod account and use 13 tools for developer tools straight from your AI agent. Connect with your own API key. The Cloud Built for AI - GPU cloud computing platform for AI and machine learning workloads.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_runpod?ms=1787291520000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `runpod_create_cluster`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/runpod`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/runpod/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/runpod/create/cluster` — Tool to create a new GPU cluster for multi-node distributed computing workloads on RunPod. Use when you need to deploy multiple pods with shared configuration for parallel processing, ML training, or 
  - body: { env?: object[], type: string, ports?: string, pod_count: integer, start_ssh?: boolean, image_name?: string, throughput?: integer, volume_key?: string, deploy_cost?: number, docker_args?: string, gpu_type_id: string, template_id?: string, cluster_name?: string, volume_in_gb?: integer, start_jupyter?: boolean, data_center_id?: string, min_cuda_version?: string, gpu_count_per_pod: integer, network_volume_id?: string, volume_mount_path?: string, container_disk_in_gb?: integer, allowed_cuda_versions?: string[] }
- `POST https://api.mcp.ai/api/runpod/create/secret` — Tool to create a new secure secret in RunPod for credential management. Use when you need to store sensitive values like API keys, passwords, or tokens that will be accessible in pods and endpoints vi
  - body: { name: string, value: string, description?: string }
- `POST https://api.mcp.ai/api/runpod/delete/registry/auth` — Tool to delete container registry authentication from RunPod. Use when you need to remove stored registry credentials.
  - body: { registry_auth_id: string }
- `POST https://api.mcp.ai/api/runpod/delete/template` — Tool to remove a RunPod template via GraphQL mutation. Use when you need to delete a template that is no longer needed. The template must not be in use by any pods or assigned to any serverless endpoi
  - body: { template_name: string }
- `POST https://api.mcp.ai/api/runpod/get/gpu/types` — Tool to retrieve available GPU types and their specifications, pricing, and availability from RunPod. Use when you need to find GPU options for deployment.
  - body: { input?: object }
- `POST https://api.mcp.ai/api/runpod/get/myself` — Retrieve basic information about the authenticated user including ID, email, and security settings. Use this to get the current user's ID, email address, terms of service status, and MFA settings. Not
- `POST https://api.mcp.ai/api/runpod/get/pod` — Retrieve details of a specific RunPod pod by its unique pod ID. Returns pod configuration including GPU count, memory, cost, and status. Use when you need to check the current state or configuration o
  - body: { pod_id: string }
- `POST https://api.mcp.ai/api/runpod/list/cpu/types` — Tool to retrieve available CPU types and their specifications from RunPod. Use when you need to view CPU options for provisioning pods or selecting hardware configurations.
- `POST https://api.mcp.ai/api/runpod/save/endpoint` — Tool to create or update a RunPod serverless endpoint with GPU configuration and scaling settings. Use when configuring new GPU-accelerated serverless endpoints or modifying existing endpoint paramete
  - body: { id?: string, name: string, gpu_ids: string, locations?: string, scaler_type?: string, template_id: string, workers_max?: integer, workers_min?: integer, idle_timeout?: integer, scaler_value?: integer, network_volume_id?: string }
- `POST https://api.mcp.ai/api/runpod/save/registry/auth` — Tool to save container registry authentication credentials for accessing private Docker images in RunPod. Use when you need to store credentials for a private container registry.
  - body: { name: string, password: string, username: string }
- `POST https://api.mcp.ai/api/runpod/save/template` — Tool to create a new RunPod template or update an existing one with container configuration. Use when you need to define reusable pod/serverless configurations with specific images, environment variab
  - body: { env?: object[], name: string, ports?: string, readme?: string, image_name: string, docker_args?: string, template_id?: string, volume_in_gb: integer, is_serverless: boolean, volume_mount_path?: string, container_disk_in_gb: integer }
- `POST https://api.mcp.ai/api/runpod/update/registry/auth` — Tool to update existing container registry authentication credentials in RunPod. Use when you need to modify the username or password for an existing registry authentication.
  - body: { id: string, password: string, username: string }
- `POST https://api.mcp.ai/api/runpod/update/user/settings` — Tool to update current user settings (e.g., SSH public key) in RunPod. Use when you need to configure SSH access to pods by setting the user's SSH public key.
  - body: { pub_key: string }

## Example prompts
- "What can I do in RunPod?"
- "Show me a summary of my RunPod account"

## More
- Page: https://mcp.ai/runpod
- Agent spec (llms.txt): https://mcp.ai/runpod/llms.txt
- Postman collection: https://mcp.ai/runpod/postman.json