We put an MCP endpoint in 49 business apps. Here is what a read-only key can and cannot do to an invoice register.

Описание и применение

Унифицированный, безопасный доступ к 49 самодостаточным бизнес‑приложениям через MCP‑эндпоинт с read‑only ключами, предотвращающими запись и обеспечивающими аудит.

Задача

Integrating a Model Context Protocol (MCP) endpoint into multiple self-hosted business tools while ensuring secure, read-only access for language models.

Результат

Uniform, secure read-only AI access to 49 self-hosted business apps without exposing write capabilities or sensitive operations.

Рабочий процесс

• 1. Deploy the MCP endpoint on the self-hosted app (POST /mcp).
• 2. Generate a read-only API key (apk_…) via the app’s settings.
• 3. Configure the AI client (Claude, OpenAI, n8n, curl) with the endpoint URL, Authorization header, and optional require_approval flag.
• 4. The client sends a tools/list request; only read tools are returned.
• 5. The model can query invoices but cannot invoke write, delete, or email tools.
• 6. All actions are logged with the key’s user for audit.
• 7. If write access is needed, generate a separate key with appropriate permissions and set require_approval to "never" if desired.

Доказательства

When you mint a key you choose what it may do. Pick read only, and the endpoint stops advertising the tools that change anything.

Источник

Everything a read-and-write key does lands in the audit log with the key's user beside it.

Источник