run_repl · Replit MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_repl does on Replit MCP Server

AI agents invoke run_repl to trigger actions in Replit MCP Server. 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.

WHY IT NEEDS A POLICY

Why run_repl needs a policy

This tool directly executes code in a Replit workspace. Even though the workspace contents could be benign, an AI agent could use create_file and run_repl together to execute arbitrary code. The blast radius is high because Replit workspaces can perform any operation the environment permits (file I/O, network requests, subprocess execution, etc.).

From the tool's definition Tool description states 'Start/run a Replit workspace', which triggers execution of arbitrary code within that workspace.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_repl Rate-limited

run_repl 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Replit MCP Server, so you can run agents against it safely.

FAQ

Questions about run_repl

What does the run_repl tool do? +

Start/run a Replit workspace. It is categorised as a Execute tool in the Replit MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_repl? +

Register the Replit MCP Server MCP server in PolicyLayer and add a rule for run_repl: 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 Replit MCP Server. Nothing to install.

What risk level is run_repl? +

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

Can I rate-limit run_repl? +

Yes. Add a rate_limit block to the run_repl 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 run_repl completely? +

Set action: deny in the PolicyLayer policy for run_repl. 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 run_repl? +

run_repl is provided by the Replit MCP Server MCP server (nova-3951/replit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.