Code Execution & Sandboxes MCP servers

DMCPS: Highly secure, isolated MCP server environment giving AI agents sandboxed shell access.

Audit Dockerfiles for root users, baked-in secrets, curl-pipe-shell and unpinned base images.

A paid remote MCP for Equibles, built to return verdicts, receipts, usage logs, and audit-ready JSON

Essential MCP server: HTTP, web search, downloads, Wolfram|Alpha, shell, JS, file I/O, memory.

Find every leaked secret on your machine — API keys in .env files, shell history, and configs.

MCP server: filesystem, shell diagnostics, Microsoft Graph (stdio, no API key — use env + optional per-call graph token).

Kubernetes Port Forward — MCP Server: port-forward Kubernetes services with terminal integration

File-based comms protocol for AI-to-AI dialogue between terminal agents.

Buy .vn and international domains in VND from the terminal; search and reserve without an account

Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.

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

Pact 5 tooling: REPL test runs, trap scanning, gas estimation, interface diff, format checks.

Hosts, metrics, Docker and authorized_keys over a macOS terminal's live SSH connections

Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.

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

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

Self-hosted MCP for controlled AI development and staging without a general-purpose remote shell.

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

Salesforce sandbox seeding CLI + MCP server: SOQL-scoped org-to-org copy with dependency-graph walking, cross-org FK remapping, deterministic PII masking, and a hard AI-never-sees-your-data boundary.

Ephemeral MicroVM-isolated code execution for AI agents. Fresh VM per call, hard-purged after.

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

Safe shell argument escaping for bash, cmd.exe, and PowerShell.

Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.

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

Terminal Telegram client over MTProto: CLI for messages, media and contacts, plus an MCP server that sends notifications when new messages arrive.

A real interactive terminal for AI agents (MCP). Run and test vim, htop, gdb, REPLs, and any TUI — things the built-in fire-and-forget terminal can't touch.

MCP server: persistent tmux-backed shell sessions for AI agents — interactive commands, REPLs, ssh, dev servers

An MCP server that enables AI agents to ask users clarifying questions via pop-up terminal windows.

Marketing MCP: content, SEO, outbound, LinkedIn, ads. Agents provision a sandbox with one POST.

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

Local long-term memory for terminal coding agents: blueprints, code anchors and distilled lessons in one JSON file, restoring project context across sessions.

Kanta CLI + MCP server — email verification, email finding, and the Kanta B2B contact database from your terminal or an MCP client.

Your runbooks, as agent tools. Declare scripts in a runbooks.json manifest and serve them to Claude Code, Cursor and any MCP client as typed, allowlisted tools - no free text ever reaches your shell.

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

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

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

Pay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights.

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

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

Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.

JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support.

Read-only ArcadeOps discovery for developer docs, OAuth, OpenAPI and synthetic sandbox.

Axon MCP server — local non-custodial trading terminal for AI agents. ~35 typed Model Context Protocol tools for Hyperliquid perps, Uniswap V3 spot, Aave V3 lending, GMX v2 perps across Arbitrum, Base, Avalanche, Polygon, Optimism. Drop-in for Claude Code

Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.

Structured B2B supply search, quoting, sandbox orders and fulfillment status for agents.

Persistent tmux terminal for AI agents — real-time spectating, SSH host-group dispatch.

Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.

RECON UGC from your terminal: search viral TikToks, read breakdowns, compare videos, and run RECON as a local MCP server. Sign in with your browser, no API key.