run_pascal · Claude Pascal MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_pascal does on Claude Pascal MCP Server

AI agents invoke run_pascal to trigger actions in Claude Pascal 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.

THE RISK

High Risk

Why run_pascal needs a policy

This tool executes Pascal/Delphi code on local or remote (Android) systems. While the tool description is empty, the server's explicit purpose and sibling ADB tools establish that run_pascal triggers code execution with side effects dependent on the Pascal program's arguments and logic. This falls under Execute rather than Write because it runs compiled programs/scripts rather than merely storing data.

From the tool's definition Tool name 'run_pascal' combined with server description stating it 'compile[s], run[s], and interact[s] with Pascal/Delphi desktop applications' and 'GUI automation' indicates execution of arbitrary code.

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

POLICY

How to control run_pascal

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

policy.json

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

run_pascal 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 Claude Pascal 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 Claude Pascal MCP Server tools

Destructive paserver_remove paserver_remove Destructive sim_uninstall Uninstall an app from a simulator. Destructive sim_shutdown Shut down a simulator. Pass udid='booted' to stop all running ones. Destructive sim_terminate Terminate a running app by bundle identifier. Execute adb_launch_app adb_launch_app Execute adb_stop_app Force-stop an app on the Android device. Execute build_dproj build_dproj Execute compile_delphi_project compile_delphi_project

All 53 Claude Pascal 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 Claude Pascal 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 run_pascal

What does the run_pascal tool do? +

run_pascal. It is categorised as a Execute tool in the Claude Pascal 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_pascal? +

Register the Claude Pascal MCP Server MCP server in PolicyLayer and add a rule for run_pascal: 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 Claude Pascal MCP Server. Nothing to install.

What risk level is run_pascal? +

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

Can I rate-limit run_pascal? +

Yes. Add a rate_limit block to the run_pascal 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_pascal completely? +

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

run_pascal is provided by the Claude Pascal MCP Server MCP server (tina4stack/claude-pascal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Pascal MCP Server tool call.

Start from Claude Pascal 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 →

Free to start. No card required.

53 Claude Pascal MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.