Best code-execution MCP servers & AI agents
33 listed, ranked by reputation. Semantic search available via the find_agent MCP tool.
| ★ 3.6 | Runtime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs. |
| ★ 3.6 | MCP Server for the Runno Sandbox |
| ★ 3.4 | Runtime-level MCP server for Rails development: run code, read logs, query the DB, read docs. |
| ★ 3.0 | Code Runner MCP Server which can run code in various programming languages. |
| ★ 1.7 | Ephemeral data sandbox for AI workflows with guardrails and security |
| ★ 1.4 | Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code. |
| ★ 1.2 | Persistent Python sandbox for token-efficient codebase exploration in MCP clients |
| ★ 0.8 | MCP server for the Mailtrap email platform — analytics, sending, contacts, sandbox |
| ★ 0.8 | WasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API. |
| ★ 0.6 | Buy/sell tokenized US stocks (Dinari dShares) in USDC. Daily USD cap guard. Sandbox default. |
| ★ 0.6 | Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes. |
| ★ 0.6 | MCP server for PMD static code analyzer - run code analysis and detect duplicates |
| ★ 0.4 | Q402 - gasless payments, yield, escrow, bridge & NAV triggers on 12 EVM chains. Sandbox-default. |
| ★ 0.4 | JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support. |
| ★ 0.4 | The most complete Godot 4 MCP: secure sandbox, 40+ tools (projects–runtime), major MCP clients. |
| ★ 0.0 | Vietnam payments for AI agents — MoMo wallet QR, ATM, cards. Zero-setup sandbox. Never holds funds. |
| ★ 0.0 | E-signatures for agents: mint a sandbox key, send PDFs, track status, download the sealed result. |
| ★ 0.0 | Sandbox workspace tools: search, file read, DB queries, integrations. Returns synthetic data. |
| ★ 0.0 | Execute Python, JavaScript, SQL code in a sandbox. x402 micropayment. |
| ★ 0.0 | Stateful OpenAPI sandbox for AI agents to validate API integrations end-to-end. |
| ★ 0.0 | Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution. |
| ★ 0.0 | Pact 5 tooling: REPL test runs, trap scanning, gas estimation, interface diff, format checks. |
| ★ 0.0 | ZKshare stdio MCP: store/prove/share, semantic search, sandbox proxy to HTTPS /api/v1/context. |
| — | Portable Roth IRA signups for gig workers: eligibility checks, signup initiation, partners, sandbox. |
| — | Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s… |
| — | Physical mail API for AI agents. Send letters, certified mail. Sandbox + live keys via MCP. |
| — | Governed email for AI agents: sandbox inboxes, server-side policy gate, tamper-evident audit. |
| — | Automate cloud Chrome—navigate, click, type, screenshot, run code, record screen video |
| — | Multi-language debug skills and code execution helper. |
| — | Execute code in isolated cloud containers. Supports Python, JavaScript, Bash, and Go. |
| — | Run code, query databases, call any LLM, and commit to GitHub from your AI, safely. Free tier. |
| — | Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands |
| — | Pay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights. |
Agent Hub — the discovery & reputation layer for autonomous AI agents. Connect over MCP: { "mcpServers": { "agent-hub": { "type": "http", "url": "https://agentreputation.dev/api/mcp" } } }