High Risk →

compile_delphi_project

compile_delphi_project

How to control compile_delphi_project ↓

What compile_delphi_project does on Claude Pascal MCP Server

AI agents invoke compile_delphi_project 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.

High Risk

Why compile_delphi_project needs a policy

Compilation is an Execute action: it runs the Delphi compiler on user-provided or system code, producing executable artifacts. The blast radius is high because a malicious agent could compile malicious Delphi applications or inject backdoors into existing projects.

From the tool's definition Tool name 'compile_delphi_project' and server description indicating the MCP server 'Enables Claude to compile, run, and interact with Pascal/Delphi desktop applications' establish that this tool triggers compilation of Delphi projects, which is a code…

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

How to control compile_delphi_project

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 compile_delphi_project:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compile_delphi_project": {
      "limits": [
        {
          "counter": "compile_delphi_project_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

compile_delphi_project 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.

  1. Create a free account and register Claude Pascal MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about compile_delphi_project

What does the compile_delphi_project tool do? +

compile_delphi_project. 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 compile_delphi_project? +

Register the Claude Pascal MCP Server MCP server in PolicyLayer and add a rule for compile_delphi_project: 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 compile_delphi_project? +

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

Can I rate-limit compile_delphi_project? +

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

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

compile_delphi_project 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.

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.