# Coding Agents

> What a coding agent working on your project can reach, what it is never allowed to do, and how to connect Stripe and Cloudflare safely.

*Canonical: https://makerkit.dev/docs/void-cloudflare/security/coding-agents*

---

The kit is built to be driven by a coding agent (Claude Code, Codex, Cursor) while you approve logins and paste secrets yourself. Three things keep the agent away from your secrets and your live business: rules it reads, tools that never show it a secret, and settings that block the risky outside tools.

This page is part of the [Security documentation](./overview).

## What Each Server Can Reach

An MCP server is a plug-in that lets the agent use a service on your behalf: the kit itself, or an outside service like Stripe or Cloudflare. `.mcp.json` lists the ones this project connects to. `.codex/config.toml` gives Codex the first two only.

| Server | Where it runs | What it can reach |
|---|---|---|
| `makerkit` | Your computer (`tooling/mcp-server`) | This project's files, the settings in `apps/web/.env` (secret values always hidden as `[REDACTED]`), the database on this computer only, and the kit's commands. Never a database on another computer. |
| `better-auth` | `https://mcp.better-auth.com/mcp` | Better Auth's public documentation. Nothing of yours. |
| `cloudflare-api` | `https://mcp.cloudflare.com/mcp` | The Cloudflare account you sign in with, limited to the permissions you grant when you connect it. |
| `stripe` | `https://mcp.stripe.com` | The Stripe account or sandbox you sign in with, limited to the permissions you grant when you connect it. |

## What the Agent Is Never Allowed to Do

These rules live in the project's `AGENTS.md`, which every agent reads first:

| Never | Instead |
|---|---|
| Read `apps/web/.env` | `kit_status`, `kit_doctor` or `kit_env_read` (secret values come back hidden); `kit_env_update` changes one setting |
| `void secret put KEY=value`, or any secret typed into a command | You run `pnpm --filter web exec void secret put KEY` in your own terminal; it asks you for the value |
| `void db execute --remote`, `void db studio --remote` | Database changes as migrations (`void db generate`), and the deploy and go-live steps in the [deployment](../deployment/overview) and [go-live](../billing/go-live) guides |
| `void db push` on your real database | Migrations; `void db push` only on a throwaway database |
| Ask you to paste a Stripe or Cloudflare secret into the chat | You put it in `apps/web/.env` or run `void secret put` yourself |

## Blocked Outside Tools

`.claude/settings.json` blocks the outside tools that change money or infrastructure. Claude Code refuses them even if the agent tries, and a block in the project's settings wins over anything your own settings allow.

| Server | Blocked | Still allowed |
|---|---|---|
| `stripe` | `stripe_api_write` (any create, update or delete), `send_money`, `transfer_money`, `convert_currency`, `setup_recipient`, `atlas_company_formation` | Reading data (`stripe_api_read`), searching the API and the docs, account info |
| `cloudflare-api` | `execute` (it runs every request, reads and writes alike) | `search`, `docs`, `whoami` |

Changes go through the kit's own commands instead (`pnpm billing:setup`, `pnpm kit:doctor`), which show you what they will do and ask before any live or production change. Deploys run in your own terminal ([Production Deploys](../deployment/production)).

The same file lets the agent run the kit's read-only commands without asking you each time: `pnpm kit:doctor`, `pnpm kit:doctor --launch`, `pnpm billing:doctor`, `pnpm billing:setup --plan`, and the tools `kit_doctor`, `kit_status`, `kit_journeys`, `kit_prerequisites`, `kit_db_status`, `kit_env_schema` and `kit_env_read`.

The blocks match these server names, and the official Stripe plugin for Claude Code (`plugin_stripe_stripe`). If you also added Stripe or Cloudflare another way (a claude.ai connector, another plugin), turn that one off: its tools have other names and aren't blocked. Codex, Cursor and other tools don't read `.claude/settings.json`; there, the `AGENTS.md` rules and the permissions you grant when you connect each server are what protect you.

## Connecting Stripe and Cloudflare Safely

- **Stripe:** use a sandbox, Stripe's test copy of your account (https://docs.stripe.com/sandboxes explains how to create one). When the Stripe sign-in page opens, pick that sandbox, not your live account.
- **Cloudflare:** when the Cloudflare sign-in page lists permissions, tick only the ones ending in "Read". The kit's deploy runs in your own terminal with your own login.

The blocks are a guardrail, not a vault: an agent with a terminal can still run commands. What protects you is that live keys and production secrets never reach the agent, and that live and production changes need your yes in your own terminal.

---

**Back to:** [Security overview](./overview)
