Runpod Official Plugins
by
Equips AI coding agents with a complete set of skills to provision, manage, and interact with Runpod GPU pods, serverless endpoints, templates, and volumes through the Runpod MCP server.
Runpod Official Plugins Overview
What is Runpod Official Plugins about?
Runpod Official Plugins ships a single plugin that bundles a router skill, lane skills, MCP journey skills, and a hosted Runpod MCP server configuration. It enables AI agents such as Claude Code, Codex, Gemini, Cursor, Copilot, and many others to control GPU workloads on Runpod—pods, server‑less endpoints, jobs, templates, and storage—using plain English commands.
How to use Runpod Official Plugins?
- Install the skills (works for all supported agents):
npx skills add runpod/runpod-plugins-official - Install optional CLIs you may need:
curl -sSL https://cli.runpod.net | bash # runpodctl (infra CLI) uv tool install runpod-flash # flash (serverless deployment) - Add the hosted MCP server (guided, OAuth or API‑key based):
npx @runpod/mcp-server@latest add - Set the API key (one key covers both CLIs and the MCP server):
export RUNPOD_API_KEY=<YOUR_API_KEY> # optionally persist with runpodctl doctor runpodctl doctor - Ask your agent in natural language, e.g.:
- "list my Runpod endpoints"
- "spin up an A100 pod"
- "deploy this handler to serverless"
Key Features
- Unified router skill that directs queries to the appropriate lane.
- MCP journey skills for structured tool calls to the Runpod MCP server.
- Built‑in support for runpodctl, flash, and companion CLIs (docker, gh, hf, aws).
- Hosted Runpod MCP server can be added with a single
npxcommand and OAuth authentication. - Concept graph & golden paths provide verified examples and rule‑based reasoning.
- Compatibility across Claude Code, Codex, Gemini, Cursor, Copilot, Windsurf, Cline, opencode and many other agents.
- Automatic updates via the marketplace; manual update commands available.
Use Cases
- Rapid GPU pod provisioning for AI model training or inference directly from an agent.
- Serverless endpoint deployment of custom handlers without leaving the chat interface.
- Cost‑audit and resource monitoring through MCP journey tools.
- Template‑driven pod creation using official Runpod templates.
- Migration assistance from older GraphQL/REST APIs to the latest Runpod REST v2.
- Educational assistance: agents can explain concepts (pods, volumes, GPU selection) using the built‑in usage skill.
FAQ
Q: Which agents are supported? A: Claude Code, Codex, Gemini, Cursor, Copilot, Windsurf, Cline, opencode, and any agent that can read the marketplace manifest (≈17+ agents).
Q: Do I need to install the MCP server manually?
A: No. When you add the plugin in Claude Code the MCP server is auto‑wired. For other agents run npx @runpod/mcp-server@latest add.
Q: How is authentication handled?
A: A single Runpod API key is used for runpodctl and flash. The MCP server can authenticate via OAuth (no key on disk) or by passing the same key as a Bearer token.
Q: Can I update the plugin without reinstalling?
A: Yes. Use the marketplace update commands (e.g., /plugin marketplace update runpod for Claude Code, codex plugin marketplace upgrade runpod for Codex, or re‑run the npx skills add command).
Q: How do I remove the plugin?
A: Use the uninstall commands specific to each client (e.g., /plugin uninstall runpod@runpod in Claude Code, codex plugin marketplace remove runpod, or npx skills remove runpod).
Q: Where are the concept definitions and golden paths?
A: They live under plugins/runpod/skills/runpod-usage/concepts/ and plugins/runpod/skills/runpod/golden-paths/. Agents pull them on‑demand when you ask for examples or detailed guidance.
Runpod Official Plugins's README
Runpod Official Plugins
The official plugin marketplace of skills for AI agents to manage GPU workloads on Runpod —
pods, serverless endpoints, jobs, templates, and volumes — via the Runpod MCP
server, runpodctl, and flash.
This repo ships one plugin, runpod, that bundles a router skill,
the lane skills it routes to, the MCP journey skills, the hosted Runpod MCP server config,
worked golden paths and a concept graph of how Runpod works. You install and use it as a plugin, exactly as
below; the npm package described under Also on npm is an extra way for
programs to read the same content.
Compatibility: installs as a native plugin in Claude Code, Codex, Gemini, and opencode (with auto-update), and as skills via skills.sh for Cursor, Copilot, Windsurf, Cline, and 17+ other agents — all from the same manifest.
Using an AI agent? Point it to https://docs.runpod.io/agent-setup.md to install the Runpod skills and MCP server.
Quick start
Install — works with every agent (Claude Code, Codex, Cursor, Copilot, Windsurf, Cline, Gemini, opencode, +more). The first line is all you need; drop any others you won't use:
npx skills add runpod/runpod-plugins-official # the skills — any agent (essential)
curl -sSL https://cli.runpod.net | bash # runpodctl — infra CLI (or: brew install runpod/runpodctl/runpodctl)
uv tool install runpod-flash # flash — deploy your own code (optional; or: pip install runpod-flash)
npx @runpod/mcp-server@latest add # hosted MCP server — guided setup, OAuth (optional)
Then authenticate — one API key covers everything (from the console):
export RUNPOD_API_KEY=<key> # current shell only — add to ~/.zshrc (or ~/.bashrc) to persist
# or, to save it permanently:
runpodctl doctor # prompts for the key and writes ~/.runpod/config.toml
Now just ask in plain English — the skill drives the tools for you:
"list my Runpod endpoints" · "spin up an A100 pod" · "deploy this handler to serverless"
That's it. Notes:
- Claude Code can install natively instead (auto-wires the hosted MCP server + OAuth) — see Install → Claude Code. MCP auth details: Authentication.
- Companion CLIs (
docker/gh/hf/aws) install separately, per task — seecompanion-clis.
Install
Same repo, one manifest — pick your agent below. Every route installs the same skills (the router, the lanes and the MCP journey skills), plus a hosted Runpod MCP server for control-plane tools. Then authenticate.
Claude Code
/plugin marketplace add runpod/runpod-plugins-official
/plugin install runpod@runpod
/reload-plugins
Installing also wires up the hosted Runpod MCP server (via the bundled
.mcp.json) — no separate MCP setup. Authenticate it:
/mcp → runpod → Sign in with Runpod (OAuth; no key on disk).
Verify: /plugin shows Runpod under Installed; then ask "list my Runpod
endpoints" — it should call the MCP list-endpoints tool.
Codex
codex plugin marketplace add https://github.com/runpod/runpod-plugins-official.git
codex plugin add runpod@runpod # or: codex /plugins → "Runpod" marketplace tab → Install
Manage the source: codex plugin marketplace list · … upgrade runpod · … remove runpod.
Codex may not auto-wire the bundled MCP — if the runpod MCP tools don't appear
after install, add the hosted server manually:
codex mcp add runpod --url https://mcp.getrunpod.io/
Verify: ask a Runpod task (the skill/router should answer); once the MCP is added, "list my Runpod endpoints" should call a tool.
Everything else — Cursor, Copilot, Windsurf, Cline, opencode, Gemini (+17)
Install the skills via skills.sh (reads the same
.claude-plugin/marketplace.json):
npx skills add runpod/runpod-plugins-official
# just one skill:
npx skills add https://github.com/runpod/runpod-plugins-official/tree/main/plugins/runpod/skills/runpodctl
Gemini can also install natively via the bundled
gemini-extension.json (see your client's
extension docs). For these clients, add the MCP server yourself — the guided
installer configures most agents:
npx @runpod/mcp-server@latest add # detects your agent + sets up the hosted MCP (OAuth)
See runpod-mcp/SKILL.md for hosted vs
local (stdio) MCP setup and all client options.
Authentication
Auth is needed in two places, and one Runpod API key covers both:
| What | What it needs | How |
|---|---|---|
runpodctl + flash (the CLIs) |
RUNPOD_API_KEY (env or saved) |
export RUNPOD_API_KEY=<key>, or runpodctl doctor to save it |
| Hosted Runpod MCP server (infra tools) | OAuth or the same key | /mcp sign-in, or pass the key as a Bearer header |
Fastest path — one key, everything:
- Get an API key: Runpod console → Settings → API Keys.
- Make it available to the CLIs (
runpodctl,flash) — either way works:export RUNPOD_API_KEY=<key> # this shell only; add to ~/.zshrc / ~/.bashrc to persist runpodctl doctor # OR: prompts once and saves to ~/.runpod/config.toml (persistent) - Authenticate the MCP server — pick one:
- OAuth (easiest, no key on disk): in Claude Code,
/mcp→ runpod → Sign in with Runpod. - Reuse the key you just set:
claude mcp add --transport http runpod -s user https://mcp.getrunpod.io/ \ --header "Authorization: Bearer $RUNPOD_API_KEY"
- OAuth (easiest, no key on disk): in Claude Code,
Codex and local-stdio MCP variants are in runpod-mcp.
Companion CLIs (hf, docker, gh, aws) use their own credentials — see
companion-clis. If nothing is set up, the
runpod skill detects it and walks you through this.
Updating
The plugin is versioned: updates arrive when we cut a release (a version bump, see the CHANGELOG). Claude Code pulls the new version in the background; if it hasn't picked it up yet, force it manually:
| Client | Update command |
|---|---|
| Claude Code | /plugin marketplace update runpod then /reload-plugins |
| Codex | codex plugin marketplace upgrade runpod |
| skills.sh | re-run npx skills add runpod/runpod-plugins-official |
Uninstall
Remove the plugin (and, where applicable, the marketplace it came from):
| Client | Uninstall |
|---|---|
| Claude Code | /plugin uninstall runpod@runpod, then /plugin marketplace remove runpod |
| Codex | codex plugin marketplace remove runpod |
| skills.sh | npx skills remove runpod |
If a command reports a name mismatch, list what's installed first —
/plugin marketplace list (Claude Code) · codex plugin marketplace list (Codex) ·
npx skills list (skills.sh) — and use the name shown. Removing the marketplace also drops
the bundled hosted-MCP registration it added; if you configured the MCP separately, remove
that too (Claude Code: claude mcp remove runpod).
What's inside
Start with the runpod router; it points at the right lane.
| Skill | Use it for |
|---|---|
runpod |
Router / entrypoint. Start here when the right skill is unclear. |
runpod-mcp |
Manage infra via the Runpod MCP server's structured tool calls. |
runpodctl |
Manage infra from the CLI, plus Hub, file transfer, SSH, doctor. |
flash |
Write and deploy your own code on Runpod serverless (@remote). |
companion-clis |
Prerequisite CLIs: hf, docker, gh, aws. |
runpod-usage |
Concepts — pods/serverless, containers, storage, GPU selection, gotchas. |
runpod-templates |
Official pod templates — what each image ships, ports/paths, readiness, gotchas. |
runpod-migrate |
Migrate code from the GraphQL API or REST v1 to REST v2. |
discovery, lifecycle-crud, serverless-deploy, pod-deploy, pod-doctor, endpoint-ops, cost-audit |
MCP journeys — the step-by-step playbooks runpod-mcp routes to. |
See the plugin's README for the full guide, the
development loop, and setup. Worked end-to-end examples live in
plugins/runpod/skills/runpod/golden-paths/.
Concept graph. runpod-usage/concepts/
holds one YAML file per Runpod concept (pod, network volume, machine, worker, …), with
rules that each cite a public source. Every skill, reference doc and golden path lists the
concepts it covers, so an agent can go from a question to the exact rule and to a verified
example that uses it.
| To | Read |
|---|---|
| Browse, query, validate or serve the graph | ontology/README.md |
| Understand the concept file format | concepts/README.md |
| Add or change a concept | add-concept skill |
| Add or change a skill, reference doc or golden path | write-guide skill |
| Tag a golden path with lanes, MCP coverage and concepts | golden-paths/README.md |
Also on npm
Every release also publishes @runpod/plugin-knowledge: all the
skills, reference docs, golden paths and concepts as one JSON file, at the plugin's
version. It is for programs, not for installing the plugin. The Runpod MCP server can
depend on it to serve the same guides and concepts to agents that don't have the plugin.
Nothing changes for plugin or skills.sh users.
Ask for it by name
Plain English works for one-off actions. For anything you're designing, add one clause — "and look at the examples first":
- "Use the Runpod plugin skills and look at the examples. I want to build a speech translator: audio in, translated text out. Plan it out."
- "Use the runpod-migrate skill to move this repo from GraphQL to REST v2. Show me the inventory before you change anything."
- "Use the Runpod skills to repair the missing model links in this ComfyUI workflow, then download the approved files to my Pod."
- "Use the Runpod skills and check the examples — deploy this handler to serverless."
- "Use the Runpod skills — cheapest GPU that fits a 13B model?"
- "Use the Runpod skills and check the examples — my endpoint returns
IN_QUEUEforever."
You don't need to know which example applies; the agent picks. Worth adding either way: "show me the plan before you change anything" and "verify it with a real request" ("Running" is not "ready").
Why the extra clause helps. Skills auto-load from their description, but the
golden paths deliberately have no
SKILL.md, so agents never load them on their own — and each skill's
reference/*.md opens only on demand. Asking is what pulls them in, and they're
where the commands that were actually run against a real account live.
Repository layout
.claude-plugin/marketplace.json Claude Code / skills.sh marketplace manifest
.agents/plugins/marketplace.json Codex marketplace manifest
plugins/runpod/ the plugin (skills/ incl. runpod/golden-paths/ and
runpod-usage/concepts/, .mcp.json, manifests)
packages/knowledge/ @runpod/plugin-knowledge, the npm package built from the plugin
ontology/ concept graph tooling: validator, bundle, SQLite, graph page
hooks/ marketplace, branding & link validation
Contributing
See CONTRIBUTING.md. For the reproducible dev environment and
the static-analysis gate (ruff, mypy, bandit, shellcheck, shfmt, biome, nixfmt,
deadnix, statix — run with nix flake check), see the Nix flake guide.
License
Apache-2.0
Runpod Official Plugins Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Runpod Official Plugins
Explore related MCPs that share similar capabilities and solve comparable challenges
Sequential Thinking
Officialby modelcontextprotocol
An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.
PrivateGPT
by zylon-ai
Provides an open-source API layer that enables local OpenAI‑compatible models to be used for production AI applications, offering standardized message handling, document ingestion, retrieval‑augmented generation, tool integration, and MCP connectivity.
LibreChat
OfficialClientby danny-avila
Provides a self‑hosted ChatGPT‑style interface supporting numerous AI models, agents, code interpreter, image generation, multimodal interactions, and secure multi‑user authentication.
Goose
by block
Automates engineering tasks on local machines, executing code, building projects, debugging, orchestrating workflows, and interacting with external APIs using any LLM.
Roo Code
OfficialClientby RooCodeInc
Provides an autonomous AI coding partner inside the editor that can understand natural language, manipulate files, run commands, browse the web, and be customized via modes and instructions.
Pydantic AI
by pydantic
A Python framework that enables seamless integration of Pydantic validation with large language models, providing type‑safe agent construction, dependency injection, and structured output handling.
Mcp Use
Clientby mcp-use
A Python SDK that simplifies interaction with MCP servers and enables developers to create custom agents with tool‑calling capabilities.
Mcp Agent
Clientby lastmile-ai
Build effective agents using Model Context Protocol and simple, composable workflow patterns.
Klavis AI
Officialby Klavis-AI
Provides production‑ready MCP servers and a hosted service for integrating AI applications with over 50 third‑party services via standardized APIs, OAuth, and easy Docker or hosted deployment.