mcx_run_skill

THE RISK

High Risk

mcx_run_skill triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Documented attack patterns abuse exactly the kind of access mcx_run_skill gives an agent:

HOW TO CONTROL MCX_RUN_SKILL

PolicyLayer is an MCP gateway — it sits between your AI agents and MCX (Modular Code Execution), and nothing reaches the server without passing your rules. This is the rule we recommend for mcx_run_skill:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mcx_run_skill": {
      "limits": [
        {
          "counter": "mcx_run_skill_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

mcx_run_skill stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register MCX (Modular Code Execution) — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More MCX (Modular Code Execution) tools

Execute mcx_batch Run multiple executions and searches in one call. Bypasses throttling. Examples: - mcx_ba Execute mcx_doctor Run diagnostics to check MCX health: runtime, database, adapters, sandbox. Execute mcx_execute Execute JavaScript/TypeScript code in an isolated sandbox. NOT for file/content search - Execute mcx_spawn Run code in background, returns immediately with task ID. Examples: - mcx_spawn({ code: Write mcx_edit Edit a file. Two modes: Line mode (PREFERRED - minimal context): mcx_edit({ file_path, st Write mcx_write Create or overwrite a file. Bypasses native Write Read mcx_fetch Fetch URL, convert to markdown, index in FTS5, and optionally search. Caches 24h - same UR Read mcx_file Process file with code. File content available as $file. Supports fuzzy paths - partial n

All 18 MCX (Modular Code Execution) tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in MCX (Modular Code Execution) → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the mcx_run_skill tool do? +

Run a registered MCX skill by name. Available skills: [${skillNames}] ${skillList}. It is categorised as a Execute tool in the MCX (Modular Code Execution) MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcx_run_skill? +

Register the MCX (Modular Code Execution) MCP server in PolicyLayer and add a rule for mcx_run_skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCX (Modular Code Execution). Nothing to install.

What risk level is mcx_run_skill? +

mcx_run_skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mcx_run_skill? +

Yes. Add a rate_limit block to the mcx_run_skill rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block mcx_run_skill completely? +

Set action: deny in the PolicyLayer policy for mcx_run_skill. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides mcx_run_skill? +

mcx_run_skill is provided by the MCX (Modular Code Execution) MCP server (schizoidcock/mcx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCX (Modular Code Execution) tool call.

Deterministic rules across all 18 MCX (Modular Code Execution) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN MCX (MODULAR CODE EXECUTION) →

Free to start. No card required.

18 MCX (Modular Code Execution) tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT MCX_RUN_SKILL ON MCX (MODULAR CODE EXECUTION) DOES

// THE RISK

// HOW TO CONTROL MCX_RUN_SKILL

// EXPLORE