Lathe

Lathe

Made by Seaynic Labs. Need tools like this built around your own systems? We do that.

Lathe is an MCP bundle for anyone who handles files and media. It gives your AI assistant local tools for images, PDFs, audio and video, and OCR, plus batch runs and metadata removal. The files stay on your machine.

It is a bundle: one server made of modules, each switched on or off. Modules that arrive in an update and are off by default stay off until you turn them on.

Security card
Network	None. Lathe makes no network connections, and ffmpeg and ffprobe are restricted to local files (-protocol_whitelist file,pipe). --transport http listens on 127.0.0.1 only when you start it that way.
Files	Reads and writes files only inside the working folder (LATHE_WORKING_DIR). Reads its optional config file (/.config/lathe/config.toml). Writes one local approval log (/.local/state/lathe/approvals.jsonl).
Secrets	No keys, accounts or passwords. Nothing to store, and nothing that leaves the machine.
Read-only tools	8: image_info, pdf_info, pdf_extract_text, audio_info, video_info, ocr_image, health, lathe_modules
Writes new files	audio_convert, batch_process, image_convert, image_crop, image_optimize, image_resize, image_thumbnail, pdf_compress, pdf_merge, pdf_split, pdf_to_images, scrub_metadata, video_thumbnail, video_to_gif, video_trim: each call writes new files in the working folder and never overwrites an existing one unless the call passes overwrite=true. batch_process asks the person once per run of two or more files, and nothing else asks.
Startup cost	about 7,600 tokens for a default install (21 tools, 4 skill prompts)
Changes	Tool descriptions are locked by hash (tool-manifest.lock.json); CI fails if they change silently.

Modules

Module	What it does	On by default	Needs
images	Info, resize, convert, optimize, crop, thumbnail	yes	Pillow (always installed)
pdf	Info, text (OCR for scanned pages), merge, render pages, split, compress	yes	pdf extra; ghostscript for rendering
media	Audio and video info, audio convert, a frame, trim, GIF	yes	ffmpeg and ffprobe
ocr	Text from an image	yes	ocr extra; tesseract
batch	One operation over every file matching a glob, dry run first	no	per operation (see above)
privacy	Inspect and remove GPS, camera and author metadata	no	pdf extra, for PDFs

Lathe is free and MIT licensed. It has 21 tools by default and 23 with batch and privacy on.

Skills

Skills explain how to do a job well. Your AI assistant reads them as Agent Skills, or as MCP prompts in any MCP app.

Skill	Use it for
getting-started	Setup, the install command for each missing piece, --doctor, and the approval rules
pdf	Turning a Markdown file into a PDF with Chrome or Chromium
pdf-forms	Making a PDF with fillable text boxes and checkboxes
web-image-prep	Removing location data and shrinking a folder of photos for a website

First five minutes

1. Install: uvx --from "lathe-mcp[pdf,ocr]" lathe --version prints the version. Needs Python 3.11 or newer and uv.
2. Add Lathe to your client (see Add it to your MCP client). Set LATHE_WORKING_DIR to the folder with your files.
3. Run lathe --doctor (uvx --from "lathe-mcp[pdf,ocr]" lathe --doctor). It prints ok or FIX for each piece and the command that fixes it.
4. Ask your assistant to call lathe_modules. It lists every module, what is on, and what is missing.

Try these

Paste these into your assistant, after setting LATHE_WORKING_DIR:

1. Call lathe_modules and tell me which pieces are missing.
2. Show me the metadata in photos/trip.jpg, then make a copy without it as photos/trip-clean.jpg. (needs LATHE_PRIVACY_ENABLED=true)
3. Dry-run image_optimize on everything in photos/ into web/, then run it. (needs LATHE_BATCH_ENABLED=true)
4. Split report.pdf into parts of 5 pages in parts/.
5. Cut the first 10 seconds of clip.mp4 into clip-10s.mp4, then make a 5-second GIF from it.

Install

Lathe needs Python 3.11 or newer. With uv you don't install anything ahead of time. Choose the extras for the modules you use:

uvx --from lathe-mcp lathe --version                  # images, media and batch
uvx --from "lathe-mcp[pdf,ocr]" lathe --version       # with PDF and OCR

Pinned to this release, for a repeatable setup:

uvx --from "lathe-mcp[pdf,ocr]==0.4.1" lathe --version

Or with pip:

pip install "lathe-mcp[pdf,ocr]"

Extras: pdf (pypdf), ocr (pytesseract), full (both). The images module needs nothing extra.

Claude Code plugin

The repository is also a Claude Code plugin. Its .mcp.json pins lathe-mcp[pdf,ocr]==0.4.1, and it ships the skills in skills/. The plugin is one way to install; the MCP config below works in any client.

System programs

Lathe starts without these. lathe --doctor and the lathe_modules tool list what is missing and the command for your platform.

Program	Used by	macOS	Debian / Ubuntu
ffmpeg (includes ffprobe)	media, batch (audio)	brew install ffmpeg	sudo apt install ffmpeg
tesseract	ocr, and pdf_extract_text on scanned pages	brew install tesseract	sudo apt install tesseract-ocr
ghostscript	pdf_to_images, batch (PDF)	brew install ghostscript	sudo apt install ghostscript

Settings

Set these as environment variables in your MCP client's config, or in a config file. Lathe starts without any of them.

Variable	What it is
LATHE_WORKING_DIR	The folder Lathe reads from and writes to. Default: the folder the server starts in.
LATHE_MAX_FILE_MB	Largest input file, in MB. Default 500.
LATHE_OCR_LANG	Tesseract language code(s), e.g. eng or eng+fra. Default eng.
LATHE_<MODULE>_ENABLED	true or false. Default true for images, pdf, media and ocr; false for batch and privacy.
LATHE_BATCH_PREAPPROVED	true lets a batch run of two or more files go ahead without the approval prompt. Default false. Set it only if your client cannot show approval prompts.
LATHE_APPROVAL_LOG	Where the approval log is written. Default ~/.local/state/lathe/approvals.jsonl.

Config file (optional). Lathe also reads ~/.config/lathe/config.toml, or the file named by LATHE_CONFIG. Environment variables win over the file.

[core]
working_dir = "/Users/you/Pictures"

[ocr]
lang = "eng"

[batch]
enabled = true

[privacy]
enabled = true

Add it to your MCP client

Every client below runs Lathe as a local process over stdio. Put the env values only where you need them.

Claude Desktop: claude_desktop_config.json (Settings, Developer, Edit Config)

{
  "mcpServers": {
    "lathe": {
      "command": "uvx",
      "args": ["--from", "lathe-mcp[pdf,ocr]", "lathe"],
      "env": { "LATHE_WORKING_DIR": "/path/to/your/files", "LATHE_BATCH_ENABLED": "true", "LATHE_PRIVACY_ENABLED": "true" }
    }
  }
}

Claude Code

claude mcp add lathe -e LATHE_WORKING_DIR=/path/to/your/files -- uvx --from "lathe-mcp[pdf,ocr]" lathe

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "lathe": {
      "command": "uvx",
      "args": ["--from", "lathe-mcp[pdf,ocr]", "lathe"],
      "env": { "LATHE_WORKING_DIR": "/path/to/your/files" }
    }
  }
}

VS Code: .vscode/mcp.json (note "servers", not "mcpServers")

{
  "servers": {
    "lathe": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from", "lathe-mcp[pdf,ocr]", "lathe"],
      "env": { "LATHE_WORKING_DIR": "/path/to/your/files" }
    }
  }
}

Sonique, Hermes, OpenClaw, and other clients: any client that launches a stdio MCP server. Command uvx, arguments ["--from", "lathe-mcp[pdf,ocr]", "lathe"], plus the env values above.

Over HTTP. For clients that connect to a URL instead of starting a process:

lathe --transport http --port 8765

It serves streamable HTTP at http://127.0.0.1:8765/mcp. It listens only on your own machine by default. Put authentication in front of it before exposing it anywhere else.

Tools

Tool	Module	What it does	Asks first
health	core	Server version, working folder, and whether each external program is installed	no
lathe_modules	core	Which modules are on, what is missing (with the install command), skills, and what each tool needs	no
image_info	images	Width, height, format, mode, size, and EXIF tags	no
image_resize	images	Resize by width, height or percentage, keeping the aspect ratio	no
image_convert	images	Convert to png, jpeg, webp, avif or bmp	no
image_optimize	images	Shrink for web delivery; metadata stripped unless strip_metadata=false	no
image_crop	images	Crop a rectangle	no
image_thumbnail	images	Fit inside a square	no
pdf_info	pdf	Page count, size, encryption, title, author	no
pdf_extract_text	pdf	Text of the pages you name, or of the whole file; OCR for pages without a text layer; long text in parts	no
pdf_merge	pdf	Merge PDFs in order	no
pdf_to_images	pdf	Render pages to PNG or JPEG at a chosen DPI	no
pdf_split	pdf	Split into parts of N pages	no
pdf_compress	pdf	Lossless smaller copy: content streams and duplicate objects	no
audio_info	media	Duration, format, bitrate, sample rate, channels	no
audio_convert	media	Convert to mp3, wav, flac, aac or ogg	no
video_info	media	Duration, resolution, codec, frame rate, audio tracks	no
video_thumbnail	media	Save one frame at a time in seconds	no
video_trim	media	Cut a section (stream copy; cuts land on keyframes)	no
video_to_gif	media	Animated GIF from up to 30 seconds of video	no
ocr_image	ocr	Text from an image; long text in parts	no
batch_process	batch	One operation over every matching file; dry run by default	yes, for runs of 2+ files
scrub_metadata	privacy	Inspect (default), or write a copy without GPS, camera or author metadata	no

Every tool returns structured data with a published schema. Long text comes in parts: pass next_offset back as offset. Errors always read lathe.<module>.<code>: <message> Fix: <hint>.

Approval

Only batch_process asks, and only for a run of two or more files. The client shows the person one plan: the operation, the output folder, whether existing outputs may be replaced, the file count and up to ten file names. The person approves or declines once for the whole run. The model cannot answer for the person. A client that cannot show prompts gets approval_unavailable, with the setting that fixes it (LATHE_BATCH_PREAPPROVED=true).

Every other writing tool writes one new file per call without asking. None of them overwrites an existing file unless the call passes overwrite=true.

Files and safety

• Working folder. Relative paths resolve against LATHE_WORKING_DIR. Inputs and outputs must stay inside it. Symlinks that point outside are refused.
• Nothing is overwritten by accident. An output that already exists is refused unless the call passes overwrite=true. An output can never be the input file.
• Batch runs never touch their inputs. batch_process refuses an output folder that is the input folder, and it skips any output that already exists.
• Writes are atomic. A file is written under a temporary name and moved into place, so a failure never leaves a half-written file.
• Local only. Lathe makes no network connections, and ffmpeg and ffprobe only open local files.
• Size limit. Inputs over LATHE_MAX_FILE_MB (500 MB by default) are refused.

Security

See SECURITY.md for how to report a problem and what Lathe does not do. The approval log at ~/.local/state/lathe/approvals.jsonl records each request, approval, decline and refusal. It never records file contents.

tool-manifest.lock.json records a hash of every tool description, prompt and the server instructions. python3 scripts/tool_lock.py --check shows whether anything has changed since the release.

Develop

uv venv -p 3.11 .venv && uv pip install -p .venv/bin/python -e '.[dev]'
.venv/bin/pytest -q
python3 scripts/check_skills.py
.venv/bin/python scripts/tool_lock.py --check
.venv/bin/python scripts/security_card.py --check

The tests generate their own fixtures. Tests that need ffmpeg, tesseract or ghostscript are skipped when the program is missing.

License

MIT. Made by Seaynic Labs. Third-party libraries and programs are listed in CREDITS.md.

---

Built by Seaynic Labs. We build tools like this around a business's own systems: local-first, with a person approving every change. See custom integrations.