Runcrate

Name: Runcrate
Author: aeonmindai

Remote

runcrate.aiCloud & Infra0Updated 2d ago

Repository Visit website

About Runcrate

Runcrate is a GPU cloud service for AI developers and agents, with tools to launch instances, run jobs, schedule work, move files, and check spending. Its MCP server uses browser-based OAuth and applies the selected environment's monthly budget.

Key features

01View live GPU prices
02Launch GPUs on ready images
03Run jobs that stop machines on exit
04Schedule runs and move files
05Check spending and manage environments

Use cases

01Launch a GPU for a command-line task
02Run a training script and follow logs
03Schedule recurring GPU jobs
04Review remaining monthly budget

MCP support

The hosted Streamable HTTP MCP server exposes 47 tools for instances, jobs, schedules, files, volumes, firewall and HTTPS links, billing, environments, and secret names. It authenticates through browser OAuth and limits actions to the selected environment and its monthly budget.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.runcrate.ai/mcp

Copy install command

Claude CodeTerminalclaude mcp add --transport http aeonmindai-runcrate https://mcp.runcrate.ai/mcp

Cursor.cursor/mcp.json{"mcpServers":{"aeonmindai-runcrate":{"type":"http","url":"https://mcp.runcrate.ai/mcp"}}}Open in Cursor

VS Code.vscode/mcp.json{"servers":{"aeonmindai-runcrate":{"type":"http","url":"https://mcp.runcrate.ai/mcp"}}}Open in VS Code

Claude Desktopclaude_desktop_config.json{"mcpServers":{"aeonmindai-runcrate":{"type":"http","url":"https://mcp.runcrate.ai/mcp"}}}

Windsurf~/.codeium/windsurf/mcp_config.json{"mcpServers":{"aeonmindai-runcrate":{"serverUrl":"https://mcp.runcrate.ai/mcp"}}}

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Runcrate MCP

Give your AI agent GPUs. Runcrate is a GPU cloud for AI developers and agents: connect it once, then ask in plain words. Your agent sees live GPU prices, launches a GPU on a ready image, runs your command as a job whose machine stops (and stops billing) when the command exits, schedules runs, moves files, and checks your spend.

Server: https://mcp.runcrate.ai/mcp (streamable HTTP)
Sign-in: OAuth in your browser. No key to copy, nothing to paste into a config file.
47 tools: instances, jobs, schedules, files, volumes, firewall and HTTPS links, billing, environments and secret names. Tool reference

You pick one environment when you sign in. The agent acts only there, and that environment's monthly budget caps what it can spend.

Connect your agent

Paste this one line into your agent: Claude Code, Codex, Cursor, VS Code, OpenCode, or any agent that can run a command. It adds the server to itself, and its first Runcrate tool call opens your browser to sign in.

Add Runcrate's MCP server to yourself: run curl -fsSL "https://runcrate.ai/mcp.md" and follow it.

Or one click:

In Claude Code, the plugin adds the server and a skill that teaches Claude how to spend safely: /plugin marketplace add runcrateai/runcrate-mcp, then /plugin install runcrate@runcrate. In Gemini CLI: gemini extensions install https://github.com/runcrateai/runcrate-mcp.

Claude and ChatGPT on the web can't run a command, so they take the URL as a custom connector (steps below).

Set it up by hand

With the Runcrate CLI, one command connects every client it finds on your machine:

runcrate mcp install

Claude Code

claude mcp add --transport http --scope user runcrate https://mcp.runcrate.ai/mcp

Then run /mcp in Claude Code and pick runcrate: your browser opens to sign in.

Claude (claude.ai and Claude Desktop)

Open Settings > Connectors and choose Add custom connector.
Name it Runcrate and paste https://mcp.runcrate.ai/mcp.
Choose Connect and sign in to Runcrate in the window that opens.

ChatGPT

Open chatgpt.com/plugins, choose +, then Add custom MCP server.
Name it Runcrate and paste https://mcp.runcrate.ai/mcp as the URL, with OAuth.
Create it, sign in to Runcrate, then mention @Runcrate in a chat.

Codex

codex mcp add runcrate --url https://mcp.runcrate.ai/mcp

Codex opens your browser to sign in. Closed it? Run codex mcp login runcrate.

Windsurf and Devin

Run runcrate mcp install --client windsurf, or add a server in Cascade's MCP settings with the URL https://mcp.runcrate.ai/mcp. Devin CLI: devin mcp add -s user runcrate https://mcp.runcrate.ai/mcp, then devin mcp login runcrate.

Zed, Warp, Goose, Raycast and any other MCP client

Give the client the URL https://mcp.runcrate.ai/mcp and choose OAuth (dynamic registration). It signs you in through your browser on first use.

Config files

Cursor (~/.cursor/mcp.json), Warp (~/.warp/.mcp.json) and most clients:

{ "mcpServers": { "runcrate": { "url": "https://mcp.runcrate.ai/mcp" } } }

VS Code (mcp.json in your user profile):

{ "servers": { "runcrate": { "type": "http", "url": "https://mcp.runcrate.ai/mcp" } } }

Windsurf (mcp_config.json): { "mcpServers": { "runcrate": { "serverUrl": "https://mcp.runcrate.ai/mcp" } } }

Zed (settings.json): "context_servers": { "runcrate": { "url": "https://mcp.runcrate.ai/mcp" } }

Gemini CLI (~/.gemini/settings.json): { "mcpServers": { "runcrate": { "httpUrl": "https://mcp.runcrate.ai/mcp" } } }

Codex (~/.codex/config.toml):

[mcp_servers.runcrate]
url = "https://mcp.runcrate.ai/mcp"

Goose (~/.config/goose/config.yaml):

extensions:
  runcrate:
    name: Runcrate
    type: streamable_http
    uri: https://mcp.runcrate.ai/mcp
    enabled: true

Try it

Launch an H100 with the Finetune crate and run nvidia-smi.

Run python train.py on an A100 as a job, at most 2 hours, and follow the logs.

How much of this month's budget is left?

What is in this repo

File	For
`.claude-plugin/` and `.mcp.json`	Claude Code plugin and marketplace
`plugin.json` and `mcp.json`	Agent Plugins package (Cursor, ChatGPT, Codex)
`.cursor-plugin/plugin.json`	Cursor Marketplace
`gemini-extension.json`	Gemini CLI extension
`skills/runcrate/SKILL.md`	The skill every package ships: how to pick jobs or instances and keep spend in check

The server itself is hosted by Runcrate; this repo only packages the connection. It is listed in the official MCP registry as io.github.aeonmindai/runcrate.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.