Runtime
OfficialProvides a Google ADK integration for using Runtime sandboxes with Google's Agent Development Kit.
Provides a LangChain and Deep Agents sandbox backend, allowing LangChain-based agents to run code in Runtime sandboxes.
Provides an OpenAI Agents SDK integration so agents can use Runtime sandboxes as execution environments.
Provides a Pydantic AI integration for running agents with Runtime sandboxes.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Runtime
The SDKs, CLI, MCP server and agent integrations for Runtime: sandboxes for AI agents. Each sandbox is a Firecracker microVM with its own Linux kernel, started from one call.
npm install withruntime # TypeScript SDK, the `runtime` CLI and the MCP server
pip install withruntime # Python SDK, sync and asyncimport { Sandbox } from "withruntime";
await using sbx = await Sandbox.create();
const result = await sbx.exec("python3 -c 'print(6 * 7)'");
console.log(result.exitCode, result.stdout);from withruntime import Sandbox
with Sandbox.create() as sbx:
result = sbx.exec("python3 -c 'print(6 * 7)'")
print(result.exit_code, result.stdout)The client reads RUNTIME_API_KEY, or the connection npx withruntime login
saved on this machine. A new account starts on a free trial with no card. The
quickstart takes it from there.
MCP server
The MCP server gives an agent every Runtime product as tools. It needs Node 22.12 or later and no API key. Claude Code:
claude mcp add --scope user runtime -- npx -y withruntime mcpCursor, Cline, Windsurf and other clients that take this shape:
{
"mcpServers": {
"runtime": { "command": "npx", "args": ["-y", "withruntime", "mcp"] }
}
}The first time, the server offers one tool, runtime_connect. The agent calls
it and shows a link and a code; approve Connect agent in the browser, and
every Runtime tool appears. A machine already connected with
npx withruntime login skips this step. In CI, set RUNTIME_API_KEY instead.
Clients that connect over HTTP use https://api.withruntime.com/mcp (MCP
Streamable HTTP) and sign in through the browser. The server is in the
official MCP Registry as com.withruntime/runtime. Details:
withruntime.com/docs/mcp.
Related MCP server: agent-sandbox-mcp
What is here
Path | What it is |
| The TypeScript SDK, the |
| The Python SDK: |
| LangChain and Deep Agents sandbox backend |
| The Go, Java and Ruby SDKs |
| OpenAI Agents SDK, Pydantic AI, Google ADK and smolagents integrations, each |
| Skills, rules and MCP settings for coding agents |
| The guides served at withruntime.com/docs, which the SDK tests check samples against |
Documentation
TypeScript and Python
Frameworks, and moving from E2B or Daytona
How Runtime compares
Pages that answer what people ask when choosing a sandbox, each with the providers' published rates and the date they were read:
Alternatives to E2B, Daytona, Modal and Vercel Sandbox
The agent sandbox price index: every provider's rates, also as CSV and JSON
Tests
bun test in packages/cloud-sdk and python3 -m unittest discover -s tests
in sdks/python run here as they are. The suites that start Runtime's API
server in-process, including all of the Go, Java and Ruby tests, run in
Runtime's main repository before each release.
Contributing
Each release copies the SDKs here from Runtime's main repository, so each commit here is one copy, named after the versions in its source; a copy made before those versions reach npm and PyPI says so. Issues are welcome. A pull request is reviewed here and carried into the next release with its author credited.
License
Apache-2.0. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Cloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM.
Persistent Linux microVMs for agents: root, internet, sub-second resume and a public URL.
Persistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.
Linux VMs for AI agents: create VMs, run commands, edit files and open preview URLs.
Related MCP Servers
- AlicenseAqualityDmaintenanceRun AI agents in VM-isolated sandboxes on your Mac.151MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, manage, and execute code in isolated Firecracker microVM sandboxes via the MCP protocol, with support for sandbox lifecycle and file operations.3Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables time-travel debugging for AI agent sandboxes using Firecracker microVMs, with tools for code execution, file operations, and VM snapshot/restore via MCP.1MIT
- AlicenseAqualityBmaintenanceProvides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.11MIT