Code Execution MCP servers

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

A Node.js MCP server that spins up isolated Docker-based sandboxes for executing JavaScript snippets with on-the-fly npm dependency installation and clean teardown

Q402 - gasless payments, yield, escrow, bridge & NAV triggers on 12 EVM chains. Sandbox-default.

Enhanced Godot 4.5-4.7 MCP: headless+editor+bridge, secure GDScript sandbox, closed-loop AI dev.

Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots

Connect Claude Code with E2B cloud sandboxes — 29 tools for creating isolated Linux VMs, cloning repos, running commands, managing files, and performing git operations without touching the local machine.

A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.

Justfile integration that enables LLMs to execute any CLI or script commands with parameters safely and easily, with environment variable support and comprehensive testing.

Execute any LLM-generated code in a secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages

LATAM fiat ramps on Stellar for AI agents: live quotes, sandbox orders, PIX/SPEI simulation, docs

Buy/sell tokenized US stocks (Dinari dShares) in USDC. Daily USD cap guard. Sandbox default.

A Python Runtime Interpreter MCP Server that executes user-submitted code in an isolated environment.

Execution-verified code generation and verification with signed, offline-checkable certificates.

SWI-Prolog execution for LLMs with CLP(FD), negation-as-failure, and recursion. Benchmarked 90% vs 73% LLM-only accuracy on 30 logic problems.

Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.

Connect AI agents to MATLAB — execute code, run async jobs with progress reporting, get interactive Plotly plots, expose custom .m functions as tools, and monitor via live dashboard.

Secure Python sandbox — MCP servers, APIs, shells and host functions as native Python objects.

Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.

CLI framework and stdio MCP server for Flutter: scaffolding, hot reload, REPL, codegen.

Securely run LLM-generated code in isolated containers across 7 languages and 4 backends.

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

Sanctions API docs and request validation, with account-linked synthetic sandbox testing.

Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.

Stateful OpenAPI sandbox for AI agents to validate API integrations end-to-end.

Give an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it.

E-signatures for agents: mint a sandbox key, send PDFs, track status, download the sealed result.

Lean 4 MCP server: compile, prove theorems, and formalize math with Mathlib.

Approval layer for AI agent payments: budgets, rules, human approval. Sandbox, test credentials.

Safe Python interpreter based on HF Smolagents LocalPythonExecutor

Mock small-business CRM, inbox, calendar, invoicing and phone tools for testing AI agents safely.

Give your AI assistant its own AI assistants. For example: "Could you ask openai to generate an image of a dog?"

MCP server for the SLURM workload manager. Submit jobs, run YAML workflows, monitor GPU resources, manage SSH profiles, and sync files to remote HPC clusters from natural language. 14 tools spanning local SLURM and SSH-remote clusters; companion CLI and FastAPI Web UI ship in the same package.

Control Google Colab notebooks and assign GPUs (T4/L4/A100) from any AI agent. Enhanced fork of Google's colab-mcp with all tools visible at startup, OAuth GPU control, and Windows support.

ZKshare stdio MCP: store/prove/share, semantic search, sandbox proxy to HTTPS /api/v1/context.

An MCP server for running code locally via Docker and supporting multiple programming languages.

MCP server that lets LLMs execute code through the Piston remote code execution engine, with a zero-config uv setup and a ready-to-use Claude Desktop config example.

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

Code-mode MCP server: collapses N user-defined tools into a two-tool surface (executecode + docssearch). Backed by a unified capability manifest (allowedHosts / cpuMs / memoryLimitBytes) honoured across three sandbox kernels — in-process node:vm, WASM (QuickJS / Pyodide / Wasmtime), and remote microVM (E2B / Cloudflare Sandbox). Token-saving benchmark in repo CI.

WasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API.

Portable Roth IRA signups for gig workers: eligibility checks, signup initiation, partners, sandbox.

HL7 FHIR R4 health-data API for AI agents: free sandbox, 30 synthetic patients, AI-ready context.

Single exec tool running caller Python in a network-isolated locked-down sandbox.

Test FIX from Claude, ChatGPT, or Cursor: free sandbox FIX sessions or your own FIXSIM instances.

Governed local MCP gateway for workspace, sandbox, document and profile operations.

Open square for AI agents: solve sandbox-tested problems, earn Ed25519-signed proofs.

Sandbox workspace tools: search, file read, DB queries, integrations. Returns synthetic data.

Create a free sandbox object storage bucket; upload, download, list, inspect, and delete objects.

Sandbox-only MuPag MCP server for approved payments, subscriptions, refunds, and reconciliation.

Submit files and URLs to a malware sandbox, poll scans, fetch reports, hashes and IOCs.

Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.

Sandbox marketplace where AI agents hire agents for verified outcomes. Test money only.

Generate image, video, audio, 3D and vector media with 100+ AI models. Pay per generation.

Free agent cost, latency and quality analysis with a key. Evidence purchases are sandbox-only.

Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.

A NeevCloud sandbox as native tools: run commands, edit files, manage processes, snapshots.

Retired 2026-10-10. Escrow for AI-agent jobs; hosted sandbox switched off, code stays on GitHub.

Agent-to-business commerce sandbox: intents, offers, bookings. Demo data, ed25519-signed calls.