python_build

THE RISK

High Risk

Why python_build needs a policy

Building Python packages via 'python -m build' executes arbitrary code defined in build configuration files (setup.py, pyproject.toml build-backend hooks, etc.). While the primary intent is constructive, the tool invokes external code execution with effects that depend on the arguments/project context. This is Execute category rather than Write because it triggers code execution, not merely data creation.

From the tool's definition The tool description states it 'Build[s] Python packages (wheels and sdists) using modern python -m build', which invokes Python's build system.

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

POLICY

How to control python_build

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

policy.json

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

python_build 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 DevTools 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 DevTools Server tools

Destructive repo_sync Sync with remote and cleanup merged branches Execute python_venv Manage Python virtual environments (create, delete, info, list packages) Execute commitlint Run commitlint to validate commit messages Execute eslint Run ESLint on JavaScript/TypeScript files Execute go_benchmark Run Go benchmarks to measure code performance Execute go_build Build Go packages with cross-compilation and custom build flags support Execute lint_all Run all available linters based on project type Execute lint_files Run custom linting rules on project files

All 79 MCP DevTools 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 DevTools 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 python_build

What does the python_build tool do? +

Build Python packages (wheels and sdists) using modern python -m build. It is categorised as a Execute tool in the MCP DevTools 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 python_build? +

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

What risk level is python_build? +

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

Can I rate-limit python_build? +

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

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

python_build is provided by the MCP DevTools Server MCP server (rshade/mcp-devtools-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP DevTools Server tool call.

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

CHECK YOUR STACK →