Go Playground MCP Server
This MCP server integrates with the Go Playground API to execute, share, and manage Go code snippets.
Core Capabilities:
Execute Go code - Run Go code in the Go Playground sandbox with optional
go vetstatic analysis (enabled by default)Share code snippets - Generate persistent, shareable Go Playground URLs
Execute and share simultaneously - Run code and get both execution results and a shareable URL in one operation
Read from URLs - Extract Go code from existing Go Playground URLs
Execute from URLs - Run Go code directly from existing Go Playground URLs
Multiple URL format support - Works with go.dev/play/, go.dev/play/p/, and play.golang.org/p/ URLs
MCP protocol compliance - Seamless integration with Model Context Protocol clients
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Go Playground MCP Server run this Go code and share the results"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Go Playground MCP Server
A Model Context Protocol (MCP) server that integrates with the Go Playground API to execute Go code and generate shareable URLs.
š§ Features
Run Go Code: Execute Go code in the Go Playground sandbox
Share Code: Generate shareable URLs for Go code snippets
Run and Share: Execute code and get both results and share URL in one operation
Read from URL: Read Go code from existing Go Playground URLs
Execute from URL: Execute Go code from existing Go Playground URLs
MCP Integration: Full Model Context Protocol compliance
Related MCP server: Netmind Code Interpreter
šāāļø Usage
The server can be used with any MCP-compatible client. The server provides five tools:
run_go_code- Execute Go code and return resultsshare_go_code- Share Go code and get a URLrun_and_share_go_code- Execute code and get both results and share URLread_go_playground_url- Read Go code from an existing Go Playground URLexecute_go_playground_url- Execute Go code from an existing Go Playground URL
Add this to your MCP client configuration:
{
"mcpServers": {
"go-playground": {
"command": "npx",
"args": ["-y", "go-playground-mcp"]
}
}
}Examples
Reading code from a Go Playground URL
// Read code from https://go.dev/play/xyz123
const result = await mcpClient.callTool("read_go_playground_url", {
url: "https://go.dev/play/xyz123"
});Executing code from a Go Playground URL
// Execute code from https://go.dev/play/xyz123
const result = await mcpClient.callTool("execute_go_playground_url", {
url: "https://go.dev/play/xyz123",
withVet: true
});URL Formats Supported
The new URL-based tools support these Go Playground URL formats:
https://go.dev/play/<snippet-id>https://go.dev/play/p/<snippet-id>https://play.golang.org/p/<snippet-id>
š¤ Contributing
Ping me on Twitter @samuelberthe (DMs, mentions, whatever :))
Fork the project
Fix open issues or request new features
Don't hesitate ;)
Install
Clone this repository:
git clone https://github.com/samber/go-playground-mcp.git
cd go-playground-mcpInstall dependencies:
npm installBuild the project:
npm run buildRunning the Server
# Development mode
npm run dev
# Production mode
npm run build
npm startAdd this to your MCP client configuration:
{
"mcpServers": {
"go-playground": {
"command": "node",
"args": ["dist/index.js"]
}
}
}š¤ Contributors
š« Show your support
Give a āļø if this project helped you!
š License
Copyright Ā© 2025 Samuel Berthe.
This project is MIT licensed.
Available Tools
5 toolsexecute_go_playground_urlC
Execute Go code from an existing Go Playground URL
Inputs: url (required), withVet.
read_go_playground_urlA
Read Go code from an existing Go Playground URL
Inputs: url (required).
run_go_codeB
Run Go code in the Go Playground and return execution results
Inputs: code (required), withVet.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 5 tools
Most tools have clear distinct purposes: run_go_code executes provided code, share_go_code returns a URL, read_go_playground_url fetches code from a URL, and execute_go_playground_url runs code from a URL. The only potential confusion is between run_go_code and run_and_share_go_code, since the latter is a superset that also shares, but this is explicitly described.
Tool names follow a consistent verb_noun pattern (run, share, read, execute) and clearly reference the object (go_code or go_playground_url). Minor inconsistency exists between 'go_code' and 'go_playground_url' but it is not confusing, and the compound 'run_and_share_go_code' remains readable.
Five tools is well-scoped for a Go Playground server. Each tool covers a distinct interaction mode (run, share, read from URL, execute from URL, and combined run+share) without redundancy or bloat.
The tool set covers the essential Go Playground workflows: running code, sharing code, retrieving code from a URL, executing code from a URL, and a combined convenience tool. No obvious gaps exist for the stated purpose.
Maintenance
Related MCP Connectors
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
Run Python, Java, C, C++, C#, Go, Rust and 39 more languages, each run in a fresh, offline sandbox.
Compile code with thousands of compilers, inspect the assembly, and share godbolt.org links
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute sā¦
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides real-time access to Go package documentation, function signatures, and type definitions directly from pkg.go.dev. It enables LLMs to search for packages, retrieve specific versions, and access code examples from the official Go module ecosystem.28 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables secure cloud-based execution of code across 14+ programming languages within a sandboxed environment. It supports file management, standard input/output handling, and automatic generation of visual artifacts like plots and charts.MIT

sandboxapi-mcpofficial
AlicenseNot gradedqualityDmaintenanceExecute code in 8 programming languages via gVisor-sandboxed Docker containers. Supports Python, JS, TS, Go, Java, C++, C, and Bash.2MIT- AlicenseNot gradedqualityFmaintenanceProvides Go language tools for LLMs to analyze, test, and format Go code.1MIT