Skip to main content

The Office Worker — office-worker-mcp

CI PyPI version PyPI - Python Version License: MIT

The complete document MCP for AI agents. Generate, edit, secure, audit and extract professional PDF, Word, Excel and PowerPoint documents — fully local, zero API keys, deterministic and safe. Built for Hermes, Claude and Cursor via MCP.

Requirements (read this first)

Platform Path to all 30 tools
Any OS with Docker (on Windows via Docker Desktop with WSL2/Hyper-V backend) Official image — recommended: see Full setup below or docs/docker.md
Linux / macOS (bare metal) pip install "office-worker-mcp[pdf]" + system binaries for the 3 capabilities pip can't ship (LibreOffice → Office→PDF, Tesseract → OCR, Pango/Cairo → WeasyPrint; convert_to_pdf uses LibreOffice and does not need weasyprint). Run owi doctor once: it prints the exact one-line install command for your OS. The server also warns you at startup if anything is missing.
Windows (bare metal) Partial support only. Word/Excel/PPTX, PDF read/extract, security and convert_to_pdf work natively; premium PDF rendering (WeasyPrint), OCR and books do NOT — they need native C libs with no unattended Windows installer. Docker image needs WSL2/Hyper-V or Docker Desktop; on LTSC without Hyper-V there is no full-setup path. Details: docs/extras.md
pip install office-worker-mcp          # core: MCP server + CLI 'owi'

Connect it to your agent (stdio):

{ "mcpServers": { "office-worker": { "command": "office-worker-mcp" } } }

Full setup — all 30 tools, zero friction (recommended)

The core pip package covers the full document lifecycle; three capabilities need system binaries that pip cannot ship (LibreOffice for Office→PDF conversion, Tesseract for OCR, Pango/Cairo native libs for WeasyPrint). The official Docker image bundles everything and runs on any OS with Docker — on Windows it runs via Docker Desktop (WSL2/Hyper-V backend):

docker pull ghcr.io/cafra-house/office-worker-mcp:latest
{
  "mcpServers": {
    "office-worker": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-v", "${HOME}/office-worker-data:/data", "ghcr.io/cafra-house/office-worker-mcp:latest"]
    }
  }
}

Prefer bare metal? Run owi doctor after pip install — it reports exactly which capability is inactive and prints the one-line install command for your OS (apt/brew/dnf/winget). Details in docs/docker.md and docs/extras.md.

See it in action

Real documents generated by the MCP itself — no manual editing, no cloud:

Excel dashboard + native chart Executive report (Word) Native-chart deck (PPTX) Premium PDF (editorial design)
  • Excelcreate_excel structured table + autofilter + edit_excel add_chart / add_pivot native pivot sheet
  • Wordcreate_word executive report with headings, bullets and a data table, corporate theme
  • PPTXcreate_pptx multi-slide deck with a native DrawingML bar chart
  • PDFrender_document(design_mode="premium") editorial layout with metrics table

What you get

One package covers the entire document lifecycle — create → read → extract → convert → secure → sign → audit — with honest fidelity reporting (rich | clean | lossy) and proactive next_steps guidance on every creation tool.

  • Create — Word / Excel / PPTX / PDF from templates or declarative blocks; corporate themes, logos, watermarks, premium editorial design mode
  • Read & extract — structured Markdown/JSON for RAG (read_office, pdf_extract_structured) + embedded images as base64 for multimodal agents
  • Convert — PDF ↔ Office ↔ CSV bidirectionally with explicit fidelity warnings
  • Secure — irreversible redaction (pdf_redact), metadata scrubbing (scrub_metadata), password encryption (protect_office), form flattening for archival compliance
  • Sign & audit — real PAdES signatures (sign_pdf) + cryptographic verification (verify_pdf_signature), honest document diffing (document_diff)
  • Productivity — mail merge (mail_merge), native Excel pivots (add_pivot), native PPTX charts, multi-chapter books with auto TOC (create_book)
  • Onboardingowi doctor environment diagnostics with per-OS install hints; packaged skills installable via owi skill install

Efficiency (measured)

~2550 tokens/turn across 30 specialized tools vs ~6400 for a typical 47-tool CRUD suite — less bloat, more stable agents, lower cost. Measured, not claimed.

Documentation

Topic Where
Full reference of all 30 tools (returns / use when / do-not-use) docs/tools.md
Competitive comparison & why we're the one to install docs/comparison.md
Ten end-to-end conversational workflows (EN) docs/workflows.md
Optional extras ([pdf] [ocr] [sign] [book] [pptx]) & honest platform limits docs/extras.md

Develop & test

pip install -e ".[dev,book]"
pytest -q            # full suite verified on disk (46 passed)
python count_tokens.py   # live token-budget audit (2550.75 tok v0.9.0, <2600 target)

License

MIT — see LICENSE. Acknowledgements in NOTICE. Maintained by CaFra-House.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

office_worker_mcp-0.9.8.tar.gz (306.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

office_worker_mcp-0.9.8-py3-none-any.whl (280.6 kB view details)

Uploaded Python 3

File details

Details for the file office_worker_mcp-0.9.8.tar.gz.

File metadata

  • Download URL: office_worker_mcp-0.9.8.tar.gz
  • Upload date:
  • Size: 306.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.11.15

File hashes

Hashes for office_worker_mcp-0.9.8.tar.gz
Algorithm Hash digest
SHA256 3822157bfd9350df454790cc3ccf8fa1b62ed6ee0f79ba10cb96e318e4dcccda
MD5 b3c35607d95f9a68317277c00158bf39
BLAKE2b-256 3b4805cb95dbe1b1b0a60d8b70c5fbcdfd96780065933e733accef8fa33c1a32

See more details on using hashes here.

File details

Details for the file office_worker_mcp-0.9.8-py3-none-any.whl.

File metadata

File hashes

Hashes for office_worker_mcp-0.9.8-py3-none-any.whl
Algorithm Hash digest
SHA256 d20a7631dac01215bea8a5be38005bb91c6405a6dfd475670ed1be05c6fa741a
MD5 5f290b1e7e45dac7dd0d599adfb7ff59
BLAKE2b-256 2cca03f6d200a5f52b21114e210d84aa617d13c4b13f6901836604e0286c58ce

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.9.8 This release

2 files

0.9.7

2 files

0.9.6

2 files

0.9.5

2 files

0.9.4

2 files

0.9.3

2 files

0.9.2

2 files

0.9.1

2 files

0.9.0

2 files

0.2.0

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page