Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

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

Description and use

Uniform, secure read‑only access to 49 self‑hosted business apps via an MCP endpoint, preventing writes and ensuring auditability.

Problem

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

Outcome

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

Workflow

  • 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.

Evidence

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

Source

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

Source

  • Record date: 2026-09-05T18:08:12.051Z