# Drift · isolation and security — neuraldeep.tech API

> One section of the machine-readable reference. All sections: https://neuraldeep.tech/llms.txt · everything in one file: https://neuraldeep.tech/llms-full.txt

Each Drift user lives in a **per-user Docker container** with an ephemeral volume `daisy-ws-{uid}`. There's no cross-user access.

What's ensured:

- · **Sandbox boundary** — inside the container the user sees exactly `/workspace` (no uid in the path), with no mount of neighbors.
- · **SSRF guard** on MCP URLs and the `fetch_url` tool — blocks private/loopback/link-local/cloud-metadata.
- · **Auth** — every request is verified by a `dft_*` token; 5 active tokens per user, instant revoke.
- · **Access** — Drift is open to everyone whose key has Qwen: Free on Qwen 3.6, paid plans with their models, Kimi K2.6 on Starter and Pro.
- · **Session TTL** — the MCP registry lives in core memory, dropped after 720s or in the dispatch finally block.
- · **Privacy** — model request bodies are saved only if history is turned on in your hub account; otherwise only metrics remain. We don't train on your data.