Provides a Node.js-based MCP server for interacting with RunPod's API, with tools for managing cloud resources including GPU pods and serverless endpoints.
Facilitates provisioning and management of NVIDIA GPU resources through RunPod, allowing users to create and manage pods with specific NVIDIA GPU types.
Enables deployment and management of PyTorch environments through RunPod, supporting container images like runpod/pytorch for AI/ML workloads.
Supports management of Ubuntu-based containers in RunPod, including deployment of environments like Ubuntu 22.04 with CUDA support.
RunPod MCP Server
This Model Context Protocol (MCP) server enables you to interact with the RunPod REST API through Claude or other MCP-compatible clients.
Features
The server provides tools for managing:
- Pods: Create, list, get details, update, start, stop, and delete pods
- Endpoints: Create, list, get details, update, and delete serverless endpoints
- Templates: Create, list, get details, update, and delete templates
- Network Volumes: Create, list, get details, update, and delete network volumes
- Container Registry Authentications: Create, list, get details, and delete authentications
Setup
Prerequisites
- Node.js 18 or higher
- A RunPod account and API key
- Claude for Desktop or another MCP-compatible client
Installing via Smithery
To install runpod-mcp-ts for Claude Desktop automatically via Smithery:
Installation
- Clone the repository
- Install dependencies:
- Build the server:
Configuration
Set your RunPod API key as an environment variable:
You can get your API key from the RunPod console.
Running the Server
Start the server:
Setting up with Claude for Desktop
- Open Claude for Desktop
- Edit the config file:
~/Library/Application Support/Claude/claude_desktop_config.json
(macOS) or%APPDATA%\Claude\claude_desktop_config.json
(Windows) - Add the server configuration:
Make sure to replace the "args": ["/path/to/runpod-mcp-server/build/index.js"]
with the path to the build folder in the repository.
- Restart Claude for Desktop
Usage Examples
Here are some examples of how to use the server with Claude:
List all pods
Create a new pod
Create a serverless endpoint
Security Considerations
This server requires your RunPod API key, which grants full access to your RunPod account. For security:
- Never share your API key
- Be cautious about what operations you perform
- Consider setting up a separate API key with limited permissions
- Don't use this in a production environment without proper security measures
License
MIT
This server cannot be installed
A Model Context Protocol server that enables interaction with the RunPod REST API through Claude or other MCP-compatible clients for managing pods, endpoints, templates, network volumes, and container registry authentications.
Related MCP Servers
- -securityFlicense-qualityA Model Context Protocol server that allows Claude to make API requests on your behalf, providing tools for testing various APIs including HTTP requests and OpenAI integrations without sharing your API keys in the chat.Last updated -Python
- -securityAlicense-qualityA Model Context Protocol server that enables Large Language Models like Claude to manage Linode cloud resources, including listing regions, creating, viewing, deleting, and rebooting Linode instances.Last updated -1PythonMIT License
RunPod MCP Serverofficial
-securityAlicense-qualityThis Model Context Protocol server enables interaction with RunPod's REST API through Claude or other MCP-compatible clients, providing tools for managing pods, endpoints, templates, network volumes, and container registry authentications.Last updated -18JavaScriptMIT License- -securityAlicense-qualityA Model Context Protocol server that enables Claude to interact with Mattermost instances, supporting post management, channel operations, user management, and reaction management.Last updated -11TypeScriptMIT License