An MCP server that connects to Vercel API
Nothing to run from here
Sandbox as a Service is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
11
tools declared
local
runs on your machine
243
downloads
What it does
Give an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it.
Quickstart
Install it the way its author documents:
1. Download sandbox-as-a-service-mcp-1.1.0.tgz and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 360012454c96f2eecbb45eeb1f95e41aa53a6967dd9255efd3af6aabf6aa7218
The full guide: https://github.com/fstandhartinger/sandbox-as-a-service-mcp/releases/download/mcp-v1.1.0/sandbox-as-a-service-mcp-1.1.0.tgz
Publishernot claimed
SAAll 1 server
sandbox-as-a-service1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Sandbox as a Service as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
1. Download sandbox-as-a-service-mcp-1.1.0.tgz and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 360012454c96f2eecbb45eeb1f95e41aa53a6967dd9255efd3af6aabf6aa7218
The full guide: https://github.com/fstandhartinger/sandbox-as-a-service-mcp/releases/download/mcp-v1.1.0/sandbox-as-a-service-mcp-1.1.0.tgz
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Create an isolated cloud sandbox — a dedicated virtual machine you can run commands in.
No parameter schema on file.
Run a shell command inside a sandbox and wait for it to finish. Returns stdout, stderr and the exit code.
No parameter schema on file.
Write a file inside a sandbox. Use this to place a script or input data before running it.
No parameter schema on file.
Read a file back out of a sandbox — an artifact your code produced, a log, a generated report.
No parameter schema on file.
List the contents of a directory in a sandbox, with the type and size of each entry.
No parameter schema on file.
Give a server running inside the sandbox a public https URL, so a person can open it in a browser.
No parameter schema on file.
Get the current status and details of one sandbox, including when it expires.
No parameter schema on file.
List the sandboxes on this account, newest first. Use it to find sandboxes you created earlier.
No parameter schema on file.
Push a sandbox’s expiry further out so long-running work is not cut off.
No parameter schema on file.
Destroy a sandbox and stop billing for it. Everything inside is lost.
No parameter schema on file.
Show the account’s remaining credit balance and recent sandbox usage.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Sandbox as a Service or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 1.1.0 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 9 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestefd5b0597bd7db85ccd767cf3e3e3835f711abe76ba7e12ee18022c887006698
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| create_sandbox | no tags | |
| run_command | code-exec | code-exec: keyword "run_command" in tool name, parameter "command" |
| write_file | file-write | file-write: keyword "write_file" in tool name |
| read_file | sensitive-source | sensitive-source: keyword "read_file" |
| list_files | sensitive-source | sensitive-source: keyword "list_files" |
| expose_port | no tags | |
| get_sandbox | no tags | |
| list_sandboxes | no tags | |
| extend_sandbox | no tags | |
| destroy_sandbox | no tags | |
| get_usage | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
list_files → run_command
A sensitive-source → external-sink chain exists: list_files → run_command.
Supply chain and provenance
Integrityfirst-seen
Surface digestefd5b0597bd7db85
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Sandbox as a Service can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.