Runpod for Agents Lets Developers Hand Infrastructure Work to Their Coding Agents

One-step setup, tested skills and built-in safeguards give coding agents like Claude Code, Codex and Cursor a reliable way to provision, run and scale workloads on Runpod.

SAN FRANCISCO, Nov. 10, 2026 /PRNewswire/ -- Runpod, the AI developer cloud, today expanded Runpod for Agents, the tools that let developers hand infrastructure work to their coding agents. Agents can select hardware, deploy Pods or Serverless endpoints, diagnose failures and shut down resources they no longer need, working from Runpod's current documentation and tested operating procedures rather than training data. Runpod for Agents now works with all the most popular agents.

Agents already do real infrastructure work on Runpod, issuing more than half of all CLI commands on the platform. Runpod for Agents has two parts: a hosted Model Context Protocol (MCP) server that lets agents act on Runpod and consult its documentation, and a library of tested skills for common infrastructure tasks.

"Developers are already giving agents real infrastructure work, but most agents work from memory," said Zhen Lu, CEO and co-founder of Runpod. "An agent with API access isn't the same as an agent that knows how to run a workload correctly. We tested our procedures on live infrastructure. Agents check them before they act and developers remain in full control of authorization."

This release includes:

• One-step setup: Developers can direct their coding agent to agents.runpod.io. The agent installs Runpod's skills, connects to the hosted MCP server and prompts the developer for authorization. Clients that support OAuth can authenticate through the browser without an API key.
• Plugins for Claude Code, Codex and ChatGPT: Native plugins let developers manage Pods, Serverless endpoints and storage within their existing workflows.
• Action-level safeguards: Every MCP tool is categorized as read-only or destructive. Compatible clients can automatically execute read-only operations and require developer confirmation for destructive actions, such as deletions.
• Skills library: The library includes 10 core skills and 25 specialized use-case skills covering hardware selection, Pod and Serverless deployment, troubleshooting, endpoint operations and cost audits. All use-case skills are benchmarked and verified on live Runpod infrastructure.
• Integrated knowledge base: Before taking action, agents can use the MCP server to consult current Runpod documentation and operational guidelines, with cited sources. Agents can also flag inaccurate guidance directly to Runpod.
• Unified API across agents, SDKs and Terraform: The MCP server, Terraform provider 2.0, Go SDK v2 and TypeScript SDK all use Runpod's REST v2 API, providing a consistent interface for agents, scripts and infrastructure-as-code workflows.

Open Source Films, a production company that makes films using open source tools, uses agents on Runpod to provision compute as its production pipeline needs it. A scheduler queues the work and the agents bring extra capacity online on demand, increasing production throughput by approximately 10x.

"With Runpod, our agents have direct control of the compute they need. This takes us another step towards a continuous, largely autonomous production pipeline capable of tackling work that would otherwise be far beyond an independent film's resources," said Daniel Connell, Producer, LifeR | Founder, Open Source Films.

Runpod for Agents is available today at agents.runpod.io with more coming in December.

About Runpod

Runpod is the AI developer cloud. The platform provides the infrastructure AI developers need across the full lifecycle: experiment, train, fine-tune, deploy, and scale. Over 1.2 million developers build on Runpod. Specifically for AI workloads, Runpod is the fastest path from AI experiment to production. For more information, visit runpod.io.

SOURCE Runpod