Skip to main content
These are official instructions from Runpod to set up a good AI development environment for building and deploying on the Runpod platform. They are published at https://docs.runpod.io/agent-setup.md, so you can verify their origin before following them. Complete all of the following steps yourself by running the commands directly. The only exceptions are the steps explicitly marked User step: in-session commands and OAuth sign-in happen inside the agent UI or the browser, so you cannot perform them. If no user is present, follow No user in the loop instead of those steps. Never run a command that blocks on an interactive prompt.
  • Install Runpod Skills and the MCP server
Every command below is safe to re-run on a machine where setup already happened.

​
Install Runpod Skills and MCP server

Every route installs the same skills: the runpod router, the lane skills (runpod-mcp, runpodctl, flash, runpod-usage, runpod-templates, companion-clis, runpod-migrate), and the journey skills that runpod-mcp routes to (discovery, lifecycle-crud, serverless-deploy, pod-deploy, pod-doctor, endpoint-ops, cost-audit). It also wires up the hosted Runpod MCP server (https://mcp.getrunpod.io/) for control-plane tools. The skills install the Runpod CLI and Flash SDK later, on demand, the first time a task needs them. Do not install those now. Use the correct section for your agent below.

​
Claude Code

Run these two commands to install both the Runpod skills and the MCP server in one step. Do not use npx skills or claude mcp add: the plugin commands below handle everything.
Verify:
Expect Status: ✔ enabled. If the plugin is listed but disabled, run claude plugin enable runpod@runpod. If marketplace add fails with an SSH known_hosts error, the machine usually can’t reach github.com at all (common on networks that block GitHub). Check with curl -sI https://github.com before debugging SSH.
User step. Ask the user to run /reload-plugins inside Claude Code to activate the plugin, then sign in to the MCP server with /mcp → runpod → Sign in with Runpod. This uses OAuth, so no API key is created or stored. Wait for the user to confirm before reporting the MCP server as connected.

​
Install for other agents

​
1. Install the skills

This step needs Node.js 22.20 or newer. Check with node --version; if it’s older, stop and report it instead of continuing. Run the command below, replacing <agent-id> with your agent’s id from the table. Always pass --agent: without it, the installer targets every agent it knows about and prints a Failed to install block for agents that don’t apply to you.
For any other agent, run npx -y skills add --help and use the id it lists for your agent. Verify:
Expect the runpod router and the lane and journey skills listed above. If the output also mentions PromptScript or another agent you aren’t, ignore it; it doesn’t affect your install.

​
2. Register the MCP server

Use the section for your agent. Every agent connects to the same hosted server, https://mcp.getrunpod.io/, and signs in with OAuth on first Runpod tool use.

​
Codex

If the runpod MCP tools don’t appear after install, add the hosted server directly:
In Codex Desktop, the user must fully quit and reopen the app before the plugin and MCP tools appear.

​
Gemini CLI

Gemini can alternatively install natively through the plugin’s bundled gemini-extension.json. See your client’s extension documentation.

​
Pi

​
Cursor, GitHub Copilot, Windsurf, Cline, opencode, and all other agents

Add a server entry named runpod with the HTTP (streamable HTTP) transport and URL https://mcp.getrunpod.io/ to your agent’s MCP configuration. Merge it into the existing file; do not overwrite other servers. See your agent’s MCP documentation in Resources for the file location and format. Do not run npx @runpod/mcp-server@latest add yourself. It’s an interactive wizard for people at a terminal: in an agent shell it exits without writing any config, and it only supports Claude Code, Cursor, Windsurf, Claude Desktop, and VS Code. If you can’t edit your agent’s MCP config, hand it to the user:
User step. Ask the user to run npx @runpod/mcp-server@latest add in their own terminal and pick your agent.
After registering, the user approves the OAuth sign-in in the browser the first time you call a Runpod tool. If your agent can’t load skills, the MCP server serves the same playbooks: list-guides and read-guide return them, and lookup-concept and search-concepts answer questions about how Runpod works.

​
No user in the loop

When no user is present (CI, a scheduled job, an agent SDK run), nobody can do the User steps or the OAuth sign-in. Use a Runpod API key instead:
  1. Read the key from the RUNPOD_API_KEY environment variable. The runpodctl CLI and the Flash SDK read the same variable. Do not ask for the key, print it, or write it to a file. If it is not set, stop and report that it is missing.
  2. Install the skills for your agent as above. Skip /reload-plugins: the plugin loads the next time the agent starts.
  3. Connect the hosted MCP server with the key instead of OAuth:
    For other clients, add the same Authorization header to the server entry (for Gemini CLI: gemini mcp add -s user -t http -H "Authorization: Bearer $RUNPOD_API_KEY" runpod https://mcp.getrunpod.io/), or run the server locally over stdio with RUNPOD_API_KEY set: npx -y @runpod/mcp-server@latest.
  4. In headless Claude Code (claude -p), allow the Runpod skill and the MCP tools your task needs up front, for example --allowedTools "Skill(runpod:runpod-mcp)". Without Skill(runpod:runpod-mcp), the runpod-mcp skill is refused.
  5. Write the result banner below to your log. Mark anything that still needs a person with ✗.

​
Report the result

Report what you actually verified. Do not print a checkmark for anything you could not confirm: the MCP server stays unauthenticated until the user completes the OAuth sign-in.
Use ✓ verified, ⚠ needs a user action, ✗ failed. Follow the banner with the specific next action for every non-✓ line. Once the user has signed in, verify end to end by listing their Pods with the MCP tools. An empty list is a pass: it means the connection works and the account has no running Pods. If the list is empty but the user expects Pods or has a funded balance, the sign-in went to a different Runpod account. Ask the user to sign out of the runpod MCP server, sign in again with the right account, and then list Pods again. Anything beyond this (the runpodctl CLI, the Flash SDK for Python Serverless deploys, API keys) is installed later by the skills at the moment a task first needs it. Do not set those up now, unless you run without a user, as described above.

​
Feedback

Two different tools take feedback, on two different servers:
  • About these docs: submit_feedback on the Runpod docs MCP server (https://docs.runpod.io/mcp).
  • About the Runpod product or the Runpod MCP tools: report_feedback on the Runpod MCP server (https://mcp.getrunpod.io/).
Only call either one when you have something real to report. Never call them with placeholder content or in sessions that have nothing to do with Runpod.

​
Resources

For setup guides and troubleshooting, refer to each agent’s official documentation:
  • Runpod agent skills: https://docs.runpod.io/get-started/agent-skills
  • Runpod MCP servers: https://docs.runpod.io/get-started/mcp-servers
  • Runpod skills plugin (source): https://github.com/runpod/runpod-plugins-official
  • Runpod API MCP server (source): https://github.com/runpod/runpod-mcp
  • Claude Code: https://docs.anthropic.com/en/docs/claude-code/mcp
  • Codex: https://developers.openai.com/codex/mcp
  • Cursor: https://cursor.com/docs/mcp
  • Windsurf: https://docs.windsurf.com/windsurf/cascade/mcp
  • GitHub Copilot (VS Code): https://code.visualstudio.com/docs/copilot/customization/mcp-servers
  • opencode: https://opencode.ai/docs/mcp-servers
  • Cline: https://docs.cline.bot/mcp/configuring-mcp-servers
  • Gemini CLI: https://github.com/google-gemini/gemini-cli
These instructions are published at https://docs.runpod.io/agent-setup.md so you can re-verify their authenticity at any time.
Last modified on October 15, 2026