Sırdaş

Sırdaş: local document skills for agents

Teaches an agent when and how to use Sırdaş.

Start here

https://sirdas.app/skills/sirdas-documents/SKILL.md

For your AI agent

Paste this into Claude, ChatGPT or Cursor and the agent installs and configures itself by reading the Markdown version of this page.

View Markdown (for agents)

Every operation runs on the user's machine. No file, text or field leaves it, so it is safe for health, legal and financial documents.

Setup (once)

Claude Code: claude mcp add sirdas -- npx -y @sirdaspdf/mcp Other MCP clients: {"mcpServers": {"sirdas": {"command": "npx", "args": ["-y", "@sirdaspdf/mcp"]}}} Without MCP: npx sirdas <file.pdf> (add --json for machine output).

Files must live inside the allowed root (default: the directory the server starts in; change it with SIRDAS_ROOT).

The default workflow

  1. Always start with read_document. One call unlocks restricted PDFs, runs OCR on scans, identifies the type, extracts key fields with page citations, anonymizes personal data, finds tables and returns cited chunks plus next_steps.
  2. Tell the user what it is, in one line: type, pages, the 3–5 most useful fields (cite the page).
  3. Offer the next_steps proactively, as a short choice — don't run write operations without a yes.
  4. If status is needs_password or wrong_password, ask the user and call again with password. Never guess or brute-force.

Choosing the next tool

The user wants…Tool
Ask an AI about a sensitive documentprompt private_ai_answer (anonymize → answer → deanonymize_text)
Index for search / RAGpdf_to_chunks (use id as vector id; store pages, section) or prompt index_pdf_for_rag
Invoice lines or statement movements in Excelpdf_tables
Just the fields from text you already haveextract_fields
What changed between two versionscompare_pdfs
Password on / offprotect_pdf / unlock_pdf
Remove, keep or rotate pagesedit_pages
«Página X de Y», CONFIDENCIAL stampadd_page_numbers, add_watermark
Join / split / shrinkmerge_pdfs, split_pdf, compress_pdf_lossless
Training data from many PDFspdf_to_dataset, find_duplicates, check_contamination

Honesty rules

  • Type detection and field extraction are rule-based: say "looks like an invoice" and show the evidence when confidence is below 0.6.
  • Anonymization can miss unusual formats: suggest a quick review before sharing outside.
  • A watermark or copy restriction is not real protection; a password (AES-256) is.