Exec Sandbox
Single exec tool running caller Python in a network-isolated locked-down sandbox.
MCP server · by inhuman
About
Exec Sandbox is an MCP server published by inhuman. Marketplaces we read that list it: 1 (Official MCP Registry). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-14.
What it asks for
- Runs on your machine
- Secrets: 1
- Settings: 6
Requires: MCP_EXEC_AUTH_TOKEN (secret)
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: Docker image
Built from what Official MCP Registry declares.
claude mcp add --env "MCP_EXEC_AUTH_TOKEN=<YOUR_MCP_EXEC_AUTH_TOKEN>" --transport stdio mcp-exec -- docker run -i --rm -e MCP_EXEC_AUTH_TOKEN --network none --cap-drop ALL --security-opt no-new-privileges --user 65532:65532 --tmpfs /tmp:rw,noexec,nosuid,size=64m --memory 256m --pids-limit 128 --cpus 1 docker.io/idconstruct/mcp-exec:v0.5.4[mcp_servers.mcp-exec]
command = "docker"
args = ["run", "-i", "--rm", "-e", "MCP_EXEC_AUTH_TOKEN", "--network", "none", "--cap-drop", "ALL", "--security-opt", "no-new-privileges", "--user", "65532:65532", "--tmpfs", "/tmp:rw,noexec,nosuid,size=64m", "--memory", "256m", "--pids-limit", "128", "--cpus", "1", "docker.io/idconstruct/mcp-exec:v0.5.4"]
[mcp_servers.mcp-exec.env]
MCP_EXEC_AUTH_TOKEN = "<YOUR_MCP_EXEC_AUTH_TOKEN>"{
"mcpServers": {
"mcp-exec": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MCP_EXEC_AUTH_TOKEN",
"--network",
"none",
"--cap-drop",
"ALL",
"--security-opt",
"no-new-privileges",
"--user",
"65532:65532",
"--tmpfs",
"/tmp:rw,noexec,nosuid,size=64m",
"--memory",
"256m",
"--pids-limit",
"128",
"--cpus",
"1",
"docker.io/idconstruct/mcp-exec:v0.5.4"
],
"env": {
"MCP_EXEC_AUTH_TOKEN": "<YOUR_MCP_EXEC_AUTH_TOKEN>"
}
}
}
}docker run -i --rm -e "MCP_EXEC_AUTH_TOKEN=<YOUR_MCP_EXEC_AUTH_TOKEN>" --network none --cap-drop ALL --security-opt no-new-privileges --user 65532:65532 --tmpfs /tmp:rw,noexec,nosuid,size=64m --memory 256m --pids-limit 128 --cpus 1 docker.io/idconstruct/mcp-exec:v0.5.4Replace the values in angle brackets with your own. We show the names of the settings, never values.
Optional arguments it also declares: --read-only.
Optional settings it also lists: MCP_EXEC_DEFAULT_TIMEOUT_S, MCP_EXEC_MAX_OUTPUT_BYTES, MCP_EXEC_MAX_STDIN_BYTES, MCP_EXEC_MAX_TIMEOUT_S, MCP_EXEC_TRANSPORT.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 0.5.4 | Forks (GitHub): 0 Stars (GitHub): 1 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.
-
e2b com.mcparmory/e2b
Create and manage secure sandboxes for running AI agent code
-
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
-
cinch io.github.yusufkadry/cinch
Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.
-
Persistent Python sandbox for token-efficient codebase exploration in MCP clients
-
Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.
-
Execute binary-exploitation-shield-mcp
Premium agentic endpoint for binary-exploitation-shield-mcp.
-
ipybox io.github.gradion-ai/ipybox
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls
-
mcp-server io.github.declaw-ai/mcp-server
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.
-
Command wrapper MCP server for coding agents, compression, workflows, and local automation.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
MCP server for terminal commands, file operations, and process management
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call…
-
Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP servers. Detects prompt injection, API key…
-
Interactive PTY sessions for AI agents. Supports local shell, SSH, serial port, and persistent remote sessions via MCP. Enables AI agents to run interactive commands, connect to…
Has a listing on Claude Code: claude-plugins-official (5)
-
MCP server for terminal commands, file operations, and process management
-
Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy…
-
Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and…
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
Has a listing on Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Build and deploy on Val Town. Bundles the Val Town MCP server and platform skills (HTTP vals, cron/intervals, SQLite, email, OAuth, React UI, third-party integrations, templates).
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Codex Security workflows for security scans, analysis, and investigation.
Has a listing on Community GitHub marketplaces (5)
-
Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.
-
MCP server for terminal commands, file operations, and process management
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
blast-scope io.github.Atharva-Jayappa/blast-scope
Contextual blast-radius scoring for shell commands an AI agent is about to run
-
mcpship: check and publish MCP servers
Checks a remote MCP server against the Claude directory rules and guides its publication.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Build Model Context Protocol (MCP) servers in Python with the official MCP Python SDK v2 (MCPServer). Includes a skill that generates a server project and an expert agent for…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Build high-performance Model Context Protocol servers in Rust using the official rmcp SDK with async/await, procedural macros, and type-safe implementations.
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Advanced Security plugin for GitHub Copilot.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
power-automate
Build, edit, run, and debug Power Automate cloud flows via the FlowAgent MCP server — connection lifecycle, surgical edits, copy across environments, run management, and validated…
Has a listing on Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network. Sign in to Tailscale to connect your tailnet; Grok Bot joins it as one tagged device and only reaches the hosts…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
Has a listing on Docker MCP Catalog (5)
-
MCP server for terminal commands, file operations, and process management
-
Remote MCP server for the Hackle Admin API: experiments, feature flags, remote config, messaging.
-
Access to Rube's catalog of remote MCP servers.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
Has a listing on Official MCP Registry (5)
-
Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.
-
e2b com.mcparmory/e2b
Create and manage secure sandboxes for running AI agent code
-
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
-
cinch io.github.yusufkadry/cinch
Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.
-
Persistent Python sandbox for token-efficient codebase exploration in MCP clients
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.