Execute JavaScript/TypeScript code in an isolated sandbox. NOT for file/content search - use mcx_find (files) or mcx_grep (content) instead. Calling Adapters Adapters are available as globals. Use camelCase for names with hyphens: - supabase.list_projects() - chromeDevtools.listPages() // chrome-...
AI agents invoke mcx_execute to trigger actions in MCX (Modular Code Execution). What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
mcx_execute 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_execute gives an agent:
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_execute:
{
"version": "1",
"default": "deny",
"tools": {
"mcx_execute": {
"limits": [
{
"counter": "mcx_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}mcx_execute 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.
Free to start. No card required.
Execute JavaScript/TypeScript code in an isolated sandbox. NOT for file/content search - use mcx_find (files) or mcx_grep (content) instead. Calling Adapters Adapters are available as globals. Use camelCase for names with hyphens: - supabase.list_projects() - chromeDevtools.listPages() // chrome-devtools → chromeDevtools - adapters[. 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.
Register the MCX (Modular Code Execution) MCP server in PolicyLayer and add a rule for mcx_execute: 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.
mcx_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mcx_execute 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.
Set action: deny in the PolicyLayer policy for mcx_execute. 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.
mcx_execute 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.
Deterministic rules across all 18 MCX (Modular Code Execution) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 MCX (Modular Code Execution) tools catalogued and risk-classified — across an index of 42,500+ MCP servers.