Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.IronSecCo/ironclaw

OCI · GHCR.IO/IRONSECCO/IRONCLAW-MCP:V0.1.530 · SCANNED SEP 21

Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.

36 Trust /100
Trust breakdown (7 categories)

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 & Transparency35
Schema Quality & AI Usability83
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 197 tokens (~197/item across 1 items; 1 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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
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; "sandbox_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
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail

Unverified: 2 categories

Categories scored 0 because we could not verify them: 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.

Install

How do I install the io.github.IronSecCo/ironclaw MCP server?

io.github.IronSecCo/ironclaw runs locally as a container image, launched with docker run --rm -i ghcr.io/ironsecco/ironclaw-mcp:v0.1.530. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/ironsecco/ironclaw-mcp:v0.1.530

# add to Claude Code
claude mcp add ironsecco-ironclaw -- docker run --rm -i ghcr.io/ironsecco/ironclaw-mcp:v0.1.530
// .cursor/mcp.json
{
  "mcpServers": {
    "ironsecco-ironclaw": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ironsecco-ironclaw": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ironsecco-ironclaw -- docker run --rm -i ghcr.io/ironsecco/ironclaw-mcp:v0.1.530
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ironsecco-ironclaw": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  ironsecco-ironclaw:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ironsecco-ironclaw": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "ironsecco-ironclaw": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/ironsecco/ironclaw-mcp:v0.1.530"
      ]
    }
  }
}
Changelog

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 36

    First indexed and scored.

Diagnostics

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 21 Sept 2026 · Analysed oci/ghcr.io/ironsecco/ironclaw-mcp:v0.1.530

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 →

MCP tools · 1 exposed · ~197 tokens

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 →

Tool Tokens
sandbox_exec ~197

Run a shell command (or code snippet via `sh -c`) inside an ephemeral, hardened IronClaw sandbox box and return its stdout, stderr, exit code, and containment status. By default the box runs under gVisor (runsc), which intercepts syscalls in a user-space guest kernel; it has NO network (egress is impossible), drops all Linux capabilities, runs as a non-root user with a read-only root filesystem, no-new-privileges, a restrictive seccomp profile, and is bounded by cpu/memory/pids caps. It is torn down after the command completes. Use this to execute untrusted or model-generated code safely.

NameTypeReqDescription
commandstringyesCommand to run inside the sandbox, executed via sh -c.
imagestringOptional container image override (default: the server's configured image).
timeout_secondsintegerOptional per-exec timeout override in seconds.

No output schema declared.

No examples provided.

Common questions

What is the io.github.IronSecCo/ironclaw MCP server?

io.github.IronSecCo/ironclaw is an MCP server listed in the public MCP registry as io.github.IronSecCo/ironclaw. Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container. This page covers its container image (ghcr.io/ironsecco/ironclaw-mcp:v0.1.530).

Is the io.github.IronSecCo/ironclaw MCP server safe to use?

io.github.IronSecCo/ironclaw scores 36 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 io.github.IronSecCo/ironclaw MCP server expose?

io.github.IronSecCo/ironclaw exposes 1 tool: sandbox_exec. Their descriptions and schemas cost roughly 197 tokens of context every time the server is loaded.

Is the io.github.IronSecCo/ironclaw MCP server still maintained?

io.github.IronSecCo/ironclaw is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.