devserver_start

THE RISK

High Risk

Why devserver_start needs a policy

This tool triggers an external operation (starting a server) whose effects depend on arguments and system state. While the operation is not inherently destructive or financial, it executes code that modifies system state by launching a listening service.

From the tool's definition Tool name 'devserver_start' and description 'Start a static file server for PROJECT_ROOT' indicate execution of a server process with potential side effects dependent on the PROJECT_ROOT argument and network configuration.

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

POLICY

How to control devserver_start

PolicyLayer is an MCP gateway — it sits between your AI agents and 8th Wall MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for devserver_start:

policy.json

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

devserver_start 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 8th Wall MCP Server — 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

Related tools and policies

More 8th Wall MCP Server tools

Destructive desktop_remove_component Remove a custom component from the project Destructive project_delete_file Delete a file under PROJECT_ROOT Execute devserver_stop Stop the static file server Execute generate_custom_javascript ⚠️ WEB PROJECTS ONLY - NOT FOR DESKTOP! Generate A-Frame components for web-based projects Write assets_download_url Download a file by URL into project/assets/ Write apply_experience_template Apply a pre-configured AR experience template. This automatically sets up components, code Write assets_unzip Unzip a .zip file into project assets directory Write create_ar_experience Create a complete AR experience from a natural language description. This tool automatical

All 64 8th Wall MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in 8th Wall MCP Server → 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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about devserver_start

What does the devserver_start tool do? +

Start a static file server for PROJECT_ROOT. It is categorised as a Execute tool in the 8th Wall 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 devserver_start? +

Register the 8th Wall MCP Server MCP server in PolicyLayer and add a rule for devserver_start: 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 8th Wall MCP Server. Nothing to install.

What risk level is devserver_start? +

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

Can I rate-limit devserver_start? +

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

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

devserver_start is provided by the 8th Wall MCP Server MCP server (superdwayne/8thwallmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 8th Wall MCP Server tool call.

Start from 8th Wall MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →