// SCAN REPORT

SMART-E2B

5 tools. 3 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

3 can modify or destroy data

2 read-only

5 tools total

Community server · catalogue entry verified 04/07/2026

How to control SMART-E2B ↓

TOOL MAP

What SMART-E2B exposes to your agents

Read (2) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous SMART-E2B tools

Execute · High executeJavaScript This tool executes arbitrary JavaScript code in an isolated environment. Execute · High executePython This tool executes arbitrary Python code, which is inherently an Execute-category risk. Write · Medium uploadFile uploadFile creates new files or modifies existing file state in the sandbox through file upload.

3 of SMART-E2B's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SMART-E2B

PolicyLayer is an MCP gateway — it sits between your AI agents and SMART-E2B, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "uploadFile": {
    "limits": [
      {
        "counter": "uploadfile_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "listFiles": {
    "limits": [
      {
        "counter": "listfiles_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 SMART-E2B — 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 SMART-E2B →

Instant setup, no code required.

FULL CATALOGUE

All 5 SMART-E2B tools

EXECUTE 2 tools

Execute executeJavaScript Execute JavaScript code in a secure cloud sandbox Execute executePython Execute Python code in a secure cloud sandbox

WRITE 1 tools

Write uploadFile Upload a file to the sandbox

READ 2 tools

Read listFiles List files in a directory in the sandbox Read readFile Read a file from the sandbox

EXPLORE

Related servers

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

FAQ

Questions about SMART-E2B

How do I prevent bulk modifications through SMART-E2B? +

The SMART-E2B server has 1 write tools including uploadFile. 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 SMART-E2B.

How many tools does the SMART-E2B MCP server expose? +

5 tools across 3 categories: Execute, Read, Write. 2 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on SMART-E2B? +

Register the SMART-E2B 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 SMART-E2B tool call.

Deterministic rules across all 5 SMART-E2B tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SMART-E2B →

Instant setup, no code required.

5 SMART-E2B tools catalogued and risk-classified — across an index of 43,000+ MCP servers.