Sandbox Compute Broker
Click on "Install 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., "@Sandbox Compute BrokerAnalyze the CSV file and show an interactive dashboard"
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.
Sandbox Compute Broker
Sandbox Compute Broker lets an AI agent run compute tasks in a secure sandbox and see the results as an interactive UI — brokering every exchange so the interface and the execution environment stay safely isolated from each other.
The broker is free and open source (Apache-2.0). Your costs are hardware and ops, not API bills — there are no cloud accounts or API keys in the default path.
What it does
When an agent needs to do something computational (analyse a CSV, generate a report, run a script), it calls one of the broker's tools. The broker:
Runs the request in a sandbox — an isolated environment for untrusted code.
Reuses the session — follow-up calls hit the same sandbox so loaded datasets stay loaded.
Handles files —
/workspaceis private scratch;/outputsis surfaced only when the agent explicitly callspresent_output.Renders a UI when it helps — via MCP Apps, so results appear as an interactive dashboard instead of a wall of text. UI is optional.
agent → host → broker (OURS) → sandbox
↑ owns both sandbox connection + ui:// resourceRelated MCP server: Code Executor MCP Server
Prerequisites
Provider | What you need | Isolation |
microsandbox (default) | KVM on Linux · Apple Silicon on macOS · WHP on Windows | microVM (libkrun) |
Docker (fallback) | Docker Engine running; | OCI container (+gVisor if |
Local | Nothing | subprocess — test scaffolding only, not a security boundary |
The broker auto-selects: tries microsandbox first, falls back to Docker, bails with an
actionable error if neither is available. Override with BROKER_PROVIDER=microsandbox|docker|local.
Quickstart (under 15 minutes)
# 1. Clone + install
git clone https://github.com/your-org/sandbox-compute-broker
cd sandbox-compute-broker
npm install
# 2a. If using microsandbox (default — needs virtualization support):
# No extra steps; the SDK spawns microVMs as child processes.
# 2b. If using Docker (fallback):
docker build -t mcp-sandbox:latest sandbox-image/
# 3. Verify everything works
npx tsc -p tsconfig.json --noEmit # type-check
npx vitest run # unit tests (59 pass, no daemon needed)
# 4. Run the dashboard server
BROKER_PROVIDER=local npm run dev # local subprocess, for rapid iteration
# or:
npm run dashboard # auto-selects best available providerAdd to Claude Desktop (%APPDATA%\Claude\claude_desktop_config.json on Windows,
~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"sandbox-compute-broker": {
"command": "npx",
"args": ["tsx", "examples/dashboard/server.ts"]
}
}
}Then restart Claude Desktop and ask it to call the data_dashboard tool.
Tools exposed
Tool | UI? | What it does |
| No | Run code in the session sandbox; return stdout/stderr/exitCode. |
| No | Run an arbitrary command in the session sandbox. |
| No | Promote a |
| Yes | Run an analysis step + render an interactive App. Callbacks reuse the same sandbox. |
Output resources are read via resources/read — bytes never base64-inlined into a tool result.
Provider swap
BROKER_PROVIDER=docker npx tsx examples/dashboard/server.ts
BROKER_PROVIDER=microsandbox npx tsx examples/dashboard/server.tsZero App or tool changes required — the SandboxProvider interface is the portability
contract (see SPEC.md).
Project layout
src/
providers/
base.ts SandboxProvider interface + types (SPEC §1)
local.ts LocalSandboxProvider — subprocess, test scaffolding only
microsandbox.ts MicrosandboxProvider — microVM via libkrun (primary)
docker.ts DockerSandboxProvider — OCI container + gVisor (fallback)
index.ts selectProvider() + forceFromEnv()
session.ts SessionManager — reuse, TTL, idle reap, caps, reconnect
store.ts SessionStore interface — InMemorySessionStore + Redis stub
files.ts FileLifecycle — workspace/outputs, resource:// refs
policy.ts Policy — allow-list, egress, secrets, audit log
broker.ts MCP server — tool + ui:// registration
ui/analytics-dashboard/
app.ts In-iframe App (calls data_dashboard back)
shell.html HTML shell
build.ts esbuild bundler (produces single inline <script>)
sandbox-image/
Dockerfile Pinned OCI image (python + analysis libs)
examples/
phase0-spike/ Session-identity spike (see SPEC.md §3)
dashboard/ Phase 2 flagship: data dashboard over stdio
tests/
*.test.ts 59 tests — providers, session, files, policy, broker, limits
SPEC.md Frozen v0 provider interface + file-lifecycle contract
PLAN.md Design doc (v5)
STATUS.md Phase-by-phase implementation statusArchitecture
The four layers (PLAN.md §7):
[1] MCP App (iframe) ← @modelcontextprotocol/ext-apps (optional)
↕ postMessage / JSON-RPC
Host (Claude Desktop, …)
↕ MCP transport (stdio / streamable HTTP)
[2] MCP Broker ← src/broker.ts (OURS)
[3] Core ← session · files · policy (OURS)
↕ provider SDK
[4] Sandbox ← microsandbox microVM / Docker OCIThe App can never reach the sandbox directly (iframe isolation). Every byte flows through the broker.
Security model
Isolation level is declared by
capabilities().isolationLevelso the deployer always knows what boundary they have (subprocess | container | container+gvisor | microvm)./workspaceis never auto-exposed. The only path to the user ispresent_output.Egress is blocked by default (
disableNetwork()/--network=none). The Policy layer manages an allow-list.Secrets are injected at call time; never baked into images, code, or logs. The Policy layer redacts any configured secret values from stdout/stderr before they reach the audit log or the host.
Audit log: one JSON line per execution (
{ts, tool, provider, isolationLevel, sandboxId, exitCode, durationMs, bytesOut, policyDecisions[]}), OWASP agentic-risk mapped.
See docs/threat-model.md for the full per-edge-case analysis.
Overlap with microsandbox-mcp
microsandbox-mcp is microsandbox's own compute-only MCP server. Ours is different:
MCP Apps UI loop (interactive dashboards with App-iframe callbacks).
Provider portability: swap microsandbox ↔ Docker with one env var; the
SPEC.mdinterface lets you write third-party adapters.FileLifecycle(explicit output promotion,resource://refs, no base64 in tool results).Governance: per-tool allow-list, egress control, secret redaction, OWASP-mapped audit log.
License
Apache-2.0. AGPL adapters (Daytona) are isolated in separate packages.
SandboxCompute
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jaydeepgami56/SandboxCompute'
If you have feedback or need assistance with the MCP directory API, please join our Discord server