unstable

THE RISK

High Risk

Why unstable needs a policy

This tool deliberately triggers an exception/error as a demonstration. It executes code that throws intentionally, causing an error state. No data is read, written, or deleted — it purely executes behavior (throwing) to demonstrate error handling. Severity is low because it only throws an exception with no side effects on external data or systems.

From the tool's definition "Throws on purpose to demonstrate handler exceptions → isError"

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

POLICY

How to control unstable

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

policy.json

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

unstable 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 MCP from Scratch 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 MCP from Scratch Server tools

Execute route_support_ticket Classifies a support message via sampling/createMessage, then routes it using server-side Write add_note Registers a new demo://note/N resource and notifies list_changed. Write publish_status Updates demo://status and notifies subscribers. Write register_extra_tool Adds the greet tool at runtime and notifies tools/list_changed. Read divide Divides a by b. Returns a tool error when b is zero. Read echo Returns its input Read get_time Returns the server clock as an ISO-8601 timestamp. Read greet Returns a short greeting (registered dynamically).

All 12 MCP from Scratch 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 MCP from Scratch 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 unstable

What does the unstable tool do? +

Throws on purpose to demonstrate handler exceptions → isError. It is categorised as a Execute tool in the MCP from Scratch 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 unstable? +

Register the MCP from Scratch Server MCP server in PolicyLayer and add a rule for unstable: 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 MCP from Scratch Server. Nothing to install.

What risk level is unstable? +

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

Can I rate-limit unstable? +

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

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

unstable is provided by the MCP from Scratch Server MCP server (pguso/mcp-from-scratch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP from Scratch Server tool call.

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

CHECK YOUR STACK →