transform

A command for converting a document into clean Markdown or structured JSON using Unstructured Transform.

In plain words
What is it for?
It accepts a local file or public URL, starts and monitors a conversion job, reads the result, and reports the extracted sections and tables.
Why use it?
It turns files into text that can be reviewed, extracted, summarized, or used in other workflows.

Command

Install

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.

agentmods
npx agentmods add commands/unstructured-io/unstructured-mcp-integrations/transform
Clone the repo
git clone --depth 1 https://github.com/Unstructured-IO/unstructured-mcp-integrations
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 229 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00229
Opus 5 $0.00008 $0.00114
Sonnet 5 $0.00003 $0.00046
Haiku 4.5 $0.00002 $0.00023

Measured 2d ago against content hash 351ad213c753, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

transform/cursor/commands/transform.md · 14 lines

What it actually says

Parse the file the user names (the command argument, or the most recently shared document) using the connected transform MCP server.

  1. Determine the source. A public https:// URL can be passed directly; a local path or workspace file must be uploaded first — request an upload URL, then PUT the bytes to it.
  2. Start a transform job. Default to Markdown output unless the user asks for JSON or element/layout structure.
  3. Poll until the job completes, then read back the structured result.
  4. Summarize what was actually extracted from the result you received — pages, notable sections, and any tables visible in the output. Report element or layout counts only when JSON output was used; do not infer them from Markdown. Then ask what the user wants to do next — RAG ingestion, extraction, summarization, and so on.

If the transform server is not connected, tell the user to install the Unstructured Transform plugin and complete the OAuth sign-in on first connection.

Changes

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.

  1. 2d ago First seen · 14 lines · 15 tokens per session scan A 351ad213c753

Subscribe to this mod's changes

transform is a command published in the GitHub repository Unstructured-IO/unstructured-mcp-integrations (1 stars, last pushed 28d ago), licensed Apache-2.0. It adds 15 tokens to every session and 229 once invoked, about $0.0001 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.