RunPod MCP integration
Reports GPU availability and pricing, provisions clusters and serverless endpoints, and stores the registry credentials a private image needs.
13actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Get pod details
Lyro retrieves specifications and status of a RunPod pod to report capacity and performance. The team confirms the pod is sized correctly for the workload.
Get gpu types
Lyro lists available GPU types, their specs, pricing, and current availability on RunPod. The team selects the most cost-effective hardware for the customer's compute task.
Create runpod cluster
Lyro creates a new GPU cluster on RunPod for multi-node distributed computing workloads. The team scales compute resources elastically to meet demand.
How businesses use RunPod + Lyro
Each card is one request a support team gets, and the RunPod actions Lyro runs to close it.
Check GPU availability and pricing before committing
Lyro reports the GPU types on offer with their specifications, pricing, and current availability, lists the CPU options beside them, and reads the configuration and cost of a pod that is already running.
Get GPU TypesList CPU TypesGet Pod DetailsProvision compute for a job
Lyro creates a multi-node GPU cluster for distributed training, or saves a serverless endpoint with its GPU and scaling settings, both built on a reusable template that pins the image and resource allocation.
Create RunPod ClusterSave Serverless EndpointSave TemplateKeep private image credentials and templates tidy
Lyro stores the credentials for a private Docker registry, rotates the username or password on an existing entry, and removes a template nobody uses - a delete that fails safely while a pod still references it.
Save Container Registry AuthUpdate Registry AuthDelete TemplateSet up the credentials a pod needs at runtime
Lyro stores an API key or token as a RunPod secret, which pods and endpoints read as RUNPOD_SECRET_<name>, and sets the SSH public key on the account so whoever asked can actually reach the machine.
Create SecretUpdate User SettingsGet Authenticated User Info
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the RunPod actions it has and picks the ones a request needs.
- 01
Connect RunPod
Authorize the RunPod account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the RunPod actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about RunPod
Setup, permissions, and the limits of what Lyro can do inside RunPod.
No. The toolkit reads pod details and creates clusters, templates, and serverless endpoints, but exposes no stop, terminate, or pod-delete action. Delete Template and Delete Container Registry Authentication are the only removals available, and the template delete fails outright while any pod or serverless endpoint still uses it.
Every action available in RunPod
All 13 actions your agent can call on RunPod, straight from the live MCP connection.
Create runpod cluster
Create a new GPU cluster for multi-node distributed computing workloads on RunPod.
Create secret
Create a new secure secret in RunPod for credential management.
Delete container registry authentication
Delete container registry authentication from RunPod.
Delete template
Remove a RunPod template via GraphQL mutation.
Get gpu types
Retrieve available GPU types and their specifications, pricing, and availability from RunPod.
Get authenticated user info
Retrieve basic information about the authenticated user including ID, email, and security settings.
Get pod details
Retrieve details of a specific RunPod pod by its unique pod ID.
List cpu types
Retrieve available CPU types and their specifications from RunPod.
Save serverless endpoint
Create or update a RunPod serverless endpoint with GPU configuration and scaling settings.
Save container registry authentication
Save container registry authentication credentials for accessing private Docker images in RunPod.
Save template
Create a new RunPod template or update an existing one with container configuration.
Update registry auth
Update existing container registry authentication credentials in RunPod.
Update user settings
Update current user settings (e.g., SSH public key) in RunPod.
The tools RunPod sits next to
Same connection, same setup. Pick the next one your team already uses.
Astica.ai
Pulls printed and handwritten text out of images a customer attaches, and transcribes audio clips into text the conversation can use.
DeepImage
Submits enhancement jobs, tracks them by hash, returns the finished result URL, and clears stored images once they are delivered.
Hugging Face
Vets a model's card and security scan before adoption, runs inference, commits to Hub repositories, and watches repos through webhooks.
Modelry
Lists 3D and AR embeds, orders modeling jobs, and reports completion percentage on the ones already in progress.
Rosette text analytics
Detects the language an incoming message is written in and scores how closely two names or two addresses match before anything is acted on.
Vectorshift
Runs pipelines singly or in bulk, stops an execution by run ID, and creates, inspects, or removes the chatbots built on top of them.

Ready to connect RunPod?
Authorize the account and your agent has all 13 actions from the first conversation.


