Exec Sandbox
OCI · DOCKER.IO/IDCONSTRUCT/MCP-EXEC:V0.5.4 · SCANNED SEP 20
Single exec tool running caller Python in a network-isolated locked-down sandbox.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 61 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 387 tokens (~387/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "exec" implies "exec" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 1 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the Exec Sandbox MCP server?
Exec Sandbox runs locally as a container image, launched with docker run --rm -i docker.io/idconstruct/mcp-exec:v0.5.4. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · docker.io/idconstruct/mcp-exec:v0.5.4
claude mcp add inhuman-mcp-exec -- docker run --rm -i docker.io/idconstruct/mcp-exec:v0.5.4
{
"mcpServers": {
"inhuman-mcp-exec": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"docker.io/idconstruct/mcp-exec:v0.5.4"
]
}
}
} {
"servers": {
"inhuman-mcp-exec": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"docker.io/idconstruct/mcp-exec:v0.5.4"
]
}
}
} codex mcp add inhuman-mcp-exec -- docker run --rm -i docker.io/idconstruct/mcp-exec:v0.5.4
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"inhuman-mcp-exec": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"docker.io/idconstruct/mcp-exec:v0.5.4"
],
"enabled": true
}
}
} mcp_servers:
inhuman-mcp-exec:
command: "docker"
args: ["run", "--rm", "-i", "docker.io/idconstruct/mcp-exec:v0.5.4"] {
"McpServers": {
"inhuman-mcp-exec": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"docker.io/idconstruct/mcp-exec:v0.5.4"
]
}
}
} {
"mcpServers": {
"inhuman-mcp-exec": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"docker.io/idconstruct/mcp-exec:v0.5.4"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.80 functional
- 16 Sept 26 +1
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 −3
- Stability: pass → 0.80 functional
- 9 Sept 26 +1
- Stability: 0.97 → pass security
- 7 Sept 26 +1
- Security disclosure: unverified → fail ▼ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/docker.io/idconstruct/mcp-exec:v0.5.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
exec ~387
Execute Python code in a network-isolated sandbox and return its output. Environment: Python 3 with stdlib plus PyYAML and Jinja2. Limits: no network; wall-clock timeout defaults to 30s (max 300s); combined stdout+stderr is capped at 1048576 bytes then truncated; stdin is capped at 1048576 bytes. A non-zero exit_code or timed_out=true is a NORMAL result, not a tool error. INPUT CONTRACT — follow exactly: • `code`: Python source as a single string, newlines as \n. Top-level statements MUST start at column 0 — NO leading spaces/tabs. Indent ONLY bodies of blocks (after a line ending with ':'). Wrong: "import json\n d=json.load(...)" (leading space → IndentationError). Right: "import json\nd=json.load(...)". • `stdin`: a STRING piped to the program's stdin (read it with sys.stdin). To pass JSON, pass it AS a string — do not pass a parsed object/map. • Read input from sys.stdin, print results to stdout. Example: code="import json,sys\nd=json.load(sys.stdin)\nprint(len(d['items']))", stdin="{\"items\":[1,2,3]}" → stdout "3".
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | Python source as one string (\n for newlines). Top-level statements MUST start at column 0 (no leading spaces); indent only block bodies after a line ending in ':'. Read sys.stdin, print to stdout. |
| stdin | string | – | STRING piped to the program's stdin (max 1 MiB). To pass JSON, pass it as a string — not a parsed object. |
| timeout_s | integer | – | wall-clock timeout in seconds (default 30, clamped to [1,300]) |
| Name | Type | Req | Description |
|---|---|---|---|
| duration_ms | integer | yes | – |
| exit_code | integer | yes | – |
| stderr | string | yes | – |
| stdout | string | yes | – |
| timed_out | boolean | yes | – |
| truncated | boolean | yes | – |
No examples provided.
What is the Exec Sandbox MCP server?
Exec Sandbox is an MCP server listed in the public MCP registry as io.github.inhuman/mcp-exec. Single exec tool running caller Python in a network-isolated locked-down sandbox. This page covers its container image (docker.io/idconstruct/mcp-exec:v0.5.4).
Is the Exec Sandbox MCP server safe to use?
Exec Sandbox scores 48 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Exec Sandbox MCP server expose?
Exec Sandbox exposes 1 tool: exec. Their descriptions and schemas cost roughly 387 tokens of context every time the server is loaded.
Is the Exec Sandbox MCP server still maintained?
Exec Sandbox is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.