Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ofershap/mcp-server-anydoc --skill local-doc-to-markdowngit clone --depth 1 https://github.com/ofershap/mcp-server-anydocWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ofershap/mcp-server-anydoc/local-doc-to-markdown)<a href="https://agentmods.dev/skills/ofershap/mcp-server-anydoc/local-doc-to-markdown"><img src="https://agentmods.dev/badge/skills/ofershap/mcp-server-anydoc/local-doc-to-markdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ofershap/mcp-server-anydoc/local-doc-to-markdown"><img src="https://agentmods.dev/badge/skills/ofershap/mcp-server-anydoc/local-doc-to-markdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.00568 |
| Opus 5 | $0.00064 | $0.00284 |
| Sonnet 5 | $0.00026 | $0.00114 |
| Haiku 4.5 | $0.00013 | $0.00057 |
Grade A, and why
local-doc-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local documents to Markdown (MCP)
Use the anydoc MCP tools. Conversion runs on the user's machine. No API key. Do not upload the file to a hosted parse API unless the user asks.
Tools
| Tool | When to use |
|---|---|
convert_document |
You have a filesystem path to a PDF/Office file |
convert_base64 |
You only have file bytes in context (needs format or filename) |
list_formats |
Confirm supported extensions |
Workflow
- Prefer
convert_documentwith an absolute path when possible. - For large documents, pass
output_path(e.g../report.md) and read only the sections you need. - Use
formatonly for CSV or when the extension is missing/wrong. - If conversion fails on a scanned PDF, say OCR is required. This server is not OCR.
Defaults
- Tool choice:
convert_documentwith an absolute path. - Large files: set
output_pathand read slices from the written.md. - Unknown extension: call
list_formatsor pass explicitformat.
Error scenarios
| Symptom | Action |
|---|---|
| Scanned or image-only PDF | Tell the user OCR is not supported here; suggest an OCR pipeline elsewhere. |
| Unknown or unsupported extension | list_formats; fix path or pass format. |
convert_base64 without format |
Require format or a filename with a known extension. |
| MCP server not connected | Ask the user to add mcp-server-anydoc to MCP config, then retry. |
Rules
- Prefer MCP tools over
npx @firecrawl/anydocshell-outs when this server is connected. - Never claim the file left the machine. Conversion is local.
- Do not invent OCR, image extraction, or edit-in-place features.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 48 lines · 129 tokens per session scan A 609ac7fb5d9e
local-doc-to-markdown is a skill published in the GitHub repository ofershap/mcp-server-anydoc (0 stars, last pushed 4d ago), licensed MIT. It adds 129 tokens to every session and 568 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…
agoragentic-anydoc-document-evidence
Convert a local Word, PowerPoint, spreadsheet, OpenDocument, RTF, EPUB, CSV, or text-based PDF into bounded Markdown and an Agoragentic evidence handoff. Use when an agent needs document contents plus runtime-verified provenance, explicit evidence coverage, known-loss warnings, and a pending-or-incomplete parse…
all2md
Convert, read, generate, search, and compare documents with the all2md CLI and Python library. Use whenever a task involves reading or extracting text/tables from a document (PDF, Word, PowerPoint, Excel, HTML, email, EPUB, Jupyter, images, or 100+ source-code and text file types); converting between formats…
officecli
Use when the task involves Office document or standalone image handling such as creating, modifying, or converting PPTX, DOCX, XLSX, Report, or IMG files, and the agent should first check whether officecli supports that workflow before choosing the execution path.