About
Runno MCP Server enables secure code execution in multiple programming languages using WebAssembly WASI sandboxing. It provides a controlled environment for running Python, Ruby, JavaScript (via QuickJS), SQLite, and C code without requiring external toolchains or installations. Key capabilities: - Multi-language code execution: Python, Ruby, QuickJS (JavaScript), SQLite, and Clang (C) - WASI-based sandboxing that emulates file systems and operating systems within JavaScript - Isolated runtime environment for safe, controlled code execution - Support for interactive programs with STDIN handling via SharedArrayBuffer - Works entirely in-browser or in Node.js/JavaScript runtimes without server-side infrastructure
README
👨💻 Use Runno 👉 Runno.dev
📖 Documentation 👉 Runno.dev
Runno
Runno is a collection of JavaScript Packages for running code in various languages inside a sandbox. It's made of the following packages:
@runno/runtime - web components and headless tools for running code examples in the browser.@runno/sandbox - a secure sandbox for running code examples in Node and other JS Runtimes.@runno/wasi - an isomorphic package for running WebAssembly WASI binaries inside a sandbox.@runno/mcp - an MCP Server for running code using the @runno/sandbox package.There's also a deprecated Python package called runno
that works like the sandbox package.
This project is powered by WASI the Web Assembly System Interface. It provides a standard way for programs to interact with an operating system. By emulating this interface, we can provide a fake file system and operating system, all running within JavaScript.
Using @runno/runtime
The @runno/runtime package provides Web Components for running code in the browser.
This is very handy for programming education it means:
Quickstart
Start by adding @runno/runtime to your package:
npm install @runno/runtime
Import @runno/runtime in whatever place you'll be using the runno elements.
The simplest is in your entrypoint file (e.g. main.ts or index.ts).
import "@runno/runtime";
Once you've imported them you can use runno elements on the page.
print('Hello, World!')
For the code to run though, you'll need to set some HTTP headers:
Cross-Origin-Opener-Policy: same-origin
Cross-Origin-Embedder-Policy: require-corp
These create a cross-origin isolated context which allows the use of SharedArrayBuffer used to implement STDIN.
Supported Runtimes
The system supports a number of runtimes based on existing packages published to WAPM. These runtimes are tied to Runno and will be supported by Runno going forward.
python - Runs python3 code, not pinned to a particular version but is at least 3.6ruby - Runs standard Ruby, not pinned but is at least 3.2.0quickjs - Runs JavaScript code using the QuickJS enginesqlite - Runs SQLite commandsclang - Compiles and runs C codeclangpp - Compiles and runs C++ codephp-cgi - Runs PHP CGI compiled by VMWareRunning WASI binaries
The runtime also provides a component for running WASI binaries directly.
Examples
There are more examples for how to use Runno in the examples directory in this
repo. It includes practical ways you can use Runno, and how to configure it to
run.
Full documentation
Visit @runno/runtime to read the full documentation.
How does it work?
Runno uses Web Assembly to run code from JavaScript. Code runs in a unix-like sandbox that connects to a web-based terminal emulator. This means it behaves a lot like running code natively on a linux terminal. It's not perfect, but it's handy for making code examples run.
Plus it's pretty cool that you can just run code in your browser!
Using @runno/sandbox
Quickstart
Install the sandbox with npm install @runno/sandbox. Then use it to run code
like:
import { runCode } from "@runno/sandbox";const result = await runCode("ruby", "puts 'Hello, world!'");
if (result.resultType === "complete") {
console.log(result.stdout);
} else {
console.log("Oh no!");
}
You can also do more complicated things, like run against a virtual file system
with runFS:
function runFS(
runtime: Runtime,
entryPath: string,
fs: WASIFS,
options?: {
stdin?: string;
timeout?: number;
},
): Promise;
Using @runno/wasi
Quickstart
The quickest way to get started with Runno is by using the WASI.start class
method. It will set up everything you need and run the Wasm binary directly.
Be aware that this will run on the main thread, not inside a worker. So you will interrupt any interactive use of the browser until it completes.
```js import { WASI } from "@runno/wasi";
//...
const result = WASI.start(fetch("/binary.wasm"), {
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
context7
huynguyen03dev