// SCAN REPORT

MCX (Modular Code Execution)

18 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

7 can modify or destroy data

11 read-only

18 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCX (Modular Code Execution) ↓

TOOL MAP

Read (11) Write / Execute (7) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · Medium mcx_batch Run multiple executions and searches in one call. Bypasses throttling. Examples: - mcx_batch({ executions: [{ code: Execute · Medium mcx_doctor Run diagnostics to check MCX health: runtime, database, adapters, sandbox. Execute · Medium mcx_execute Execute JavaScript/TypeScript code in an isolated sandbox. NOT for file/content search - use mcx_find (files) or mcx_grep (content) instead Execute · Medium mcx_run_skill Run a registered MCX skill by name. Available skills: [${skillNames}] ${skillList}

7 of MCX (Modular Code Execution)'s 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MCX (MODULAR CODE EXECUTION)

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. These are the rules we recommend:

Rate limit write operations

{
  "mcx_edit": {
    "limits": [
      {
        "counter": "mcx_edit_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "mcx_fetch": {
    "limits": [
      {
        "counter": "mcx_fetch_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCX (Modular Code Execution) — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCX (MODULAR CODE EXECUTION) →

Free to start. No card required.

ALL 18 MCX (MODULAR CODE EXECUTION) TOOLS

EXECUTE 5 tools

Execute mcx_batch Run multiple executions and searches in one call. Bypasses throttling. Examples: - mcx_batch({ executions: [{ 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 - use mcx_find (files) Execute mcx_run_skill Run a registered MCX skill by name. Available skills: [${skillNames}] ${skillList} Execute mcx_spawn Run code in background, returns immediately with task ID. Examples: - mcx_spawn({ code:

WRITE 2 tools

Write mcx_edit Edit a file. Two modes: Line mode (PREFERRED - minimal context): mcx_edit({ file_path, start: 10, end: 12, ne Write mcx_write Create or overwrite a file. Bypasses native Write

READ 11 tools

Read mcx_fetch Fetch URL, convert to markdown, index in FTS5, and optionally search. Caches 24h - same URL returns cached res Read mcx_file Process file with code. File content available as $file. Supports fuzzy paths - partial names are resolved vi Read mcx_find Fast fuzzy file search with frecency ranking. Query syntax: - Read mcx_grep SIMD-accelerated content search across files. Query examples: - Read mcx_list List all available MCX adapters and skills with their methods and descriptions. Read mcx_related Find files related to a given file by analyzing imports and exports. Returns: - Files that import the given f Read mcx_search Three search modes: Mode 1: Spec Exploration (code param) Query $spec with JS. All $refs pre-resolved. - mcx Read mcx_stats Session statistics: indexed content, searches, executions, variables. Read mcx_tasks List or check background tasks started with mcx_spawn. Examples: - mcx_tasks() → list all tasks - mcx_tasks({ Read mcx_tree Navigate large JSON results without loading full content. Examples: - mcx_tree({ path: Read mcx_upgrade Get command to upgrade MCX to latest version.

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

How do I prevent bulk modifications through MCX (Modular Code Execution)? +

The MCX (Modular Code Execution) server has 2 write tools including mcx_edit, mcx_write. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCX (Modular Code Execution).

How many tools does the MCX (Modular Code Execution) MCP server expose? +

18 tools across 3 categories: Execute, Read, Write. 11 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on MCX (Modular Code Execution)? +

Register the MCX (Modular Code Execution) MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

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.

ENFORCE POLICY ON 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.

MCX (Modular Code Execution)

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MCX (MODULAR CODE EXECUTION)

// ALL 18 MCX (MODULAR CODE EXECUTION) TOOLS

// RELATED SERVERS

// FAQ