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.
git clone --depth 1 https://github.com/Unstructured-IO/unstructured-mcp-integrationsWrote 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/rules/unstructured-io/unstructured-mcp-integrations/transform)<a href="https://agentmods.dev/rules/unstructured-io/unstructured-mcp-integrations/transform"><img src="https://agentmods.dev/badge/rules/unstructured-io/unstructured-mcp-integrations/transform/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/rules/unstructured-io/unstructured-mcp-integrations/transform"><img src="https://agentmods.dev/badge/rules/unstructured-io/unstructured-mcp-integrations/transform.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 | $0.00272 | $0.00272 |
| Opus 5.5 | $0.00109 | $0.00109 |
| Sonnet 5.5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
transform 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 1mo 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.
What it actually says
unstructured-transform: When the user shares or references a document file — a PDF, DOCX, PPTX, XLSX, HTML, EML, image, or scan — and wants its contents read, summarized, extracted, or turned into structured data, use the connected transform MCP server rather than trying to read the raw bytes yourself.
Workflow:
- If the file is reachable at a public
https://URL, pass that URL straight to the transform job — no upload needed. - If it is a local path or lives in the workspace, request an upload URL first,
PUTthe bytes to it, then start the job with the returned file reference. - Start the transform job (Markdown output is the best default for reasoning over the content; use JSON when the user needs element/layout structure), poll until it finishes, then read back the structured result.
Prefer this over manual parsing for anything scanned, image-based, or table-heavy — the server handles OCR, layout, tables, chunking, and embeddings across 60+ formats. Never paste an API key into chat; the server signs in via OAuth on first use.
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.
- 1mo ago First seen · 14 lines · 272 tokens per session scan A d5b705ddcae9
transform is a cursor rule published in the GitHub repository Unstructured-IO/unstructured-mcp-integrations (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 272 tokens to every session, about $0.0011 per session on Opus 5.5. 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 cursor rules, from other repositories
sigma-reports
Build, validate, retrieve, and safely update Sigma report code representations through /v2/reports/spec. Use for fixed-layout or pixel-perfect reports, executive board packets, wide operational tables, invoices, statements, regulatory documents, PDF delivery, and bursting one copy per store/account/recipient. Covers…
citazioni
Citazioni corrette (stile numerico) e bibliografia coerente per tesi triennale in LaTeX.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.