RunPod MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNPOD_API_KEY | Yes | Your RunPod API key from the RunPod console |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 26 tools
All 26 tools have distinct names combining a unique action verb and resource noun, making each tool clearly differentiated from the others without any overlap.
Every tool follows the consistent verb_noun pattern in snake_case, using appropriate verbs like create, delete, get, list, start, stop, and update with the same set of resource nouns.
With 26 tools, the server exceeds the recommended range of 3-15 for a well-scoped set. The number feels heavy for managing five resource types, though the operations are systematic.
Most resources have full CRUD coverage plus start/stop for pods. The only missing operation is update for container-registry-auth, but overall the tool surface covers the core lifecycle actions well.