RunPod logo
ConnectorRunPod

RunPod integration for Claude and Codex

Connect RunPod once, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.

Use RunPod from Claude

Add the RunPod connection to a Space that runs Claude, then use it from every channel in that Space.

Use RunPod from Codex

Add the RunPod connection to a Space that runs Codex, then use it from every channel in that Space.

Use RunPod from Sidekick

Connect your own OpenClaw to Sidekick while type.com provides the conversations, permissions, connections, skills, and automations.

Developer Tools & IT

What the RunPod connector can do

RunPod provides on-demand GPU infrastructure for training and running AI workloads. With a RunPod connection in type.com, the agent can launch a multi-node cluster for a distributed job, store an API key or token as a secret for use inside pods, or check which GPU types are currently available, so infrastructure decisions happen alongside the rest of a project's planning in one thread.

One connection, many Spaces

Connect RunPod once, then decide which Spaces can use it in threads, skills, automations, and coding work.

What teams do with RunPod in type.com

Spin up a cluster for a training run

Ask the agent to create a multi-node GPU cluster when a job needs more than a single pod's capacity.

Try asking
Create a RunPod cluster with 4 nodes for this weekend's model training run.

Store a credential for pods to use

Have the agent create a secret so API keys are available inside pods as environment variables instead of hardcoded.

Try asking
Create a RunPod secret for our Hugging Face token so our pods can pull gated models.

Check GPU availability before deploying

Get the agent to pull current GPU types, pricing, and availability before committing to a deployment plan.

Try asking
Check available RunPod GPU types and pricing before we decide which instance to use for inference.

Representative actions

  • Create RunPod Cluster

    Deploys a multi-node GPU cluster for distributed training or parallel workloads.

  • Create Secret

    Stores a credential securely for access inside pods and endpoints as an environment variable.

  • Delete Container Registry Authentication

    Removes stored container registry credentials from the account.

  • Delete Template

    Removes a template that is not currently in use by any pod or endpoint.

  • Get GPU Types

    Returns available GPU types along with specifications, pricing, and availability.

Connection

API and auth details

RunPod provides GPU cloud infrastructure and serverless APIs for AI workloads. Integrations can manage pods, serverless endpoints, jobs, templates, networks, storage, GPU resources, usage, and AI inference pipelines using API keys and GraphQL/REST-style APIs.

FAQ

Questions people ask before connecting RunPod

Can Claude manage RunPod infrastructure from type.com?

Yes. With a RunPod connection shared to a Space, the agent can create clusters, store secrets, and check GPU availability in any thread, visible to the whole team.

How does type.com authenticate with RunPod?

RunPod uses an API key. An admin adds it once when creating the connection and chooses which Spaces can use it, so it is never typed into a prompt.

Can GPU availability checks run on a schedule?

Yes. A RunPod prompt can become a type.com automation, such as a daily check of GPU pricing before a batch job, posted to a channel.

Is this the same as an MCP server for RunPod?

Not exactly. type.com uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.

More developer tools & it connectors

All Developer Tools & IT integrations