- No uploads, no network. Neither the MCP server nor the CLI opens a network connection. They read and write local files only. On the web app the browser enforces the same thing through
Content-Security-Policy: connect-src 'self'. - Anonymization happens before anything leaves the machine. The recommended flow for cloud models is:
pdf_to_markdown(anonymized) → send placeholders to the model → map answers back locally withanonymize_text'sinclude_mapping. - Consistent pseudonyms. The same value always maps to the same placeholder inside one call, so structure and references survive.
- It is rule-based. Detection is deliberately aggressive (false positives are cheap, false negatives are not) but it can miss unusual formats. For sensitive documents, tell the user to review the output.
- Nothing is retained. No cache, no logs of document content, no telemetry. Files written by
merge/split/compressgo exactly where the user asked, and existing files are never overwritten without an explicit flag. - Verifiable. The web app ships a live outbound-traffic meter and a page explaining four checks anyone can run: https://sirdas.app/en/privacy/
Privacy model (what an agent can promise the user)
Qué garantías puede repetir un agente a sus usuarios.
Para tu agente de IA
Pega esto en Claude, ChatGPT o Cursor y el agente se instala y se configura solo, leyendo la versión en Markdown de esta página.
La documentación técnica está en inglés, que es lo que leen las herramientas y los agentes.