MCP.Market

Exec Sandbox MCP server

by inhuman·io.github.inhuman/mcp-exec·v0.5.4·1 stars

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

C65/100grade C
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed Exec Sandbox yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Exec Sandbox tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 67 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Exec Sandbox compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 20% of 48,273 servers
GitHub stars
1
more than 65% of 28,534 servers

Install Exec Sandbox in Claude Code, Cursor or VS Code

claude mcp add mcp-exec -- docker run -i --rm docker.io/idconstruct/mcp-exec:v0.5.4
Add to Cursor

What the publisher says

From the Exec Sandbox repository's README, as published. We do not edit it. Read it on GitHub

mcp-exec

English | Русский

Public OSS MCP server (Go, MIT) exposing a single powerful tool — exec — that runs caller-supplied Python code in a network-isolated, locked-down sandbox and returns stdout / stderr / exit_code. It is the "code-execution mode" building block: instead of flooding an agent's context with hundreds of tool schemas, the agent writes code that orchestrates the work.

Works over three transports — stdio / HTTP / SSE — with an identical tool set everywhere (official modelcontextprotocol/go-sdk).

The exec tool

Input: { code: string (required), timeouts?: int, stdin?: string } Output: { stdout, stderr, exitcode, durationms, truncated, timedout }

input (empty code, oversized stdin) is a tool-call error.

  • A non-zero exitcode or timedout=true is a normal result, not a tool error. Only invalid
  • Sandbox v1: Python 3 with stdlib + PyYAML, Jinja2, Pillow, numpy, pandas, matplotlib.

Security model (invariants)

Per execution: no network, non-root, cap-drop=ALL, no-new-privileges, read-only rootfs, no CAPSYSADMIN, ephemeral tmpdir (cleaned up), wall-clock timeout (kills the whole process-group), memory/PID/CPU limits, capped output (1 MiB → truncated). Runs are serialized within an instance; scale out with replicas. Caller data (code/stdin/output) is never persisted and never logged in full — only metadata.

exec is the most powerful surface there is. When embedding it in an agent, gate it behind that

agent's tool-policy (trusted roles only).

Network note: --network none only applies to stdio. In HTTP/SSE the container needs networking to serve its port, so sandboxed code would inherit egress — deny it at the orchestrator. In k8s, a NetworkPolicy that allows ingress to the port and denies all egress:

apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata: { name: mcp-exec-lockdown }
spec:
  podSelector: { matchLabels: { app: mcp-exec } }
  policyTypes: [Ingress, Egress]
  ingress: [{ ports: [{ port: 8080 }] }]
  egress: []   # deny all egress → sandbox has no network

Run

go build -o mcp-exec ./cmd/mcp-exec
MCP_EXEC_TRANSPORT=stdio ./mcp-exec

Docker (recommended production posture):

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Exec Sandbox: common questions

Is Exec Sandbox MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the Exec Sandbox safety report
How do I install Exec Sandbox?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Exec Sandbox need an API key?
Yes. The registry entry asks for MCP_EXEC_AUTH_TOKEN.
Is Exec Sandbox maintained?
The last commit was 105 days ago (2026-07-20). The latest release is v0.5.4.
How does Exec Sandbox compare with other MCP servers?
safety score 65/100 (higher than 20% of 48,273 servers); github stars 1 (more than 65% of 28,534 servers). Full comparison.

More from inhuman →