image_info
Image metadata: width, height, format, mode, file size, and EXIF tags (capped).
input_path必填
io.github.seayniclabs由 GitHub 帳號 seayniclabs 發布v0.4.1更新於 Nov 3, 2026
Local file and media tools: images, PDF, audio, video, OCR, batch and metadata. Runs locally.
發布方自己的服務:Lathe
Lathe 為 AI 助理提供本機工具,可在指定工作資料夾內檢視與轉換圖片、PDF、音訊和影片,並進行 OCR 與批次處理。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
參照 儲存庫 中的啟動說明。
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.
Lathe is free and MIT licensed. It has 21 tools by default and 23 with batch and privacy on.
Skills explain how to do a job well. Your AI assistant reads them as Agent Skills, or as MCP prompts in any MCP app.
uvx --from "lathe-mcp[pdf,ocr]" lathe --version prints the version. Needs Python 3.11 or newer and uv.LATHE_WORKING_DIR to the folder with your files.lathe --doctor (uvx --from "lathe-mcp[pdf,ocr]" lathe --doctor). It prints ok or FIX for each piece and the command that fixes it.lathe_modules. It lists every module, what is on, and what is missing.Paste these into your assistant, after setting LATHE_WORKING_DIR:
Call lathe_modules and tell me which pieces are missing.Show me the metadata in photos/trip.jpg, then make a copy without it as photos/trip-clean.jpg. (needs LATHE_PRIVACY_ENABLED=true)Dry-run image_optimize on everything in photos/ into web/, then run it. (needs LATHE_BATCH_ENABLED=true)Split report.pdf into parts of 5 pages in parts/.Cut the first 10 seconds of clip.mp4 into clip-10s.mp4, then make a 5-second GIF from it.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:
Pinned to this release, for a repeatable setup:
Or with pip:
Extras: pdf (pypdf), ocr (pytesseract), full (both). The images module needs nothing extra.
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.
Lathe starts without these. lathe --doctor and the lathe_modules tool list what is missing and the command for your platform.
Set these as environment variables in your MCP client's config, or in a config file. Lathe starts without any of them.
Config file (optional). Lathe also reads ~/.config/lathe/config.toml, or the file named by LATHE_CONFIG. Environment variables win over the file.
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)
Claude Code
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
VS Code: .vscode/mcp.json (note "servers", not "mcpServers")
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:
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.
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>.
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.
LATHE_WORKING_DIR. Inputs and outputs must stay inside it. Symlinks that point outside are refused.overwrite=true. An output can never be the input file.batch_process refuses an output folder that is the input folder, and it skips any output that already exists.LATHE_MAX_FILE_MB (500 MB by default) are refused.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.
The tests generate their own fixtures. Tests that need ffmpeg, tesseract or ghostscript are skipped when the program is missing.
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.
來源:README.md,提交 faa9114
Image metadata: width, height, format, mode, file size, and EXIF tags (capped).
input_path必填Resize an image by width, height, or percentage. Keeps the aspect ratio when only one dimension is given. Output format comes from the output extension.
widthheightoverwriteinput_path必填percentageoutput_path必填Convert an image to png, jpeg, webp, avif or bmp. The output extension must match.
format必填overwriteinput_path必填output_path必填Shrink an image for web delivery. Metadata is stripped unless strip_metadata=false.
qualityoverwriteinput_path必填output_path必填strip_metadataCrop a rectangle from an image. x and y are pixels from the top-left corner.
x必填y必填width必填height必填overwriteinput_path必填output_path必填Make a thumbnail that fits inside a square of the given size, keeping the aspect ratio.
sizeoverwriteinput_path必填output_path必填PDF metadata: page count, file size, encryption, title, author and creator.
input_path必填Extract text from a PDF, or from some pages ("2-5"). Pages with no text layer are read with OCR when it is installed. Long text comes in parts: pass next_offset as offset to continue.
pagesoffsetmax_charsinput_path必填ocr_fallbackMerge several PDFs, in the order given, into one new PDF.
overwriteinput_paths必填output_path必填Render PDF pages to PNG or JPEG files in a folder, at a chosen DPI. Needs ghostscript.
dpipagesformatoverwriteinput_path必填output_dir必填Split a PDF into parts of N pages each. Writes new PDFs into a folder and never overwrites one unless overwrite=true.
overwriteinput_path必填output_dir必填pages_per_fileWrite a smaller copy of a PDF. Lossless: it recompresses content streams and removes duplicate objects; images are not re-encoded. Writes one new file; never overwrites unless overwrite=true.
overwriteinput_path必填output_path必填Audio metadata: duration, format, bitrate, sample rate, channels and codec.
input_path必填Convert audio to mp3, wav, flac, aac or ogg. A video input keeps only its audio. The output extension must match the format.
format必填overwriteinput_path必填output_path必填Video metadata: duration, resolution, codec, frame rate, bitrate and audio tracks.
input_path必填Save one frame of a video as a PNG or JPEG, at a time in seconds.
overwritetimestampinput_path必填output_path必填Cut a section out of a video into a new file (stream copy, so it is fast and lossless; cuts land on keyframes). Never overwrites unless overwrite=true.
endstartoverwriteinput_path必填output_path必填Make an animated GIF from part of a video (up to 30 seconds, palette-optimized). Writes one new file; never overwrites unless overwrite=true.
fpsstartwidthdurationoverwriteinput_path必填output_path必填Extract the text from an image with OCR. Long text comes in parts: pass next_offset as offset to continue. lang overrides LATHE_OCR_LANG.
langoffsetmax_charsinput_path必填Server status, version, working directory, and whether each external piece is installed.
無需輸入參數。
Which modules are on, which pieces are missing (with the install command), and what each tool does. Pass a module name for its settings too.
module已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
uvx --from lathe-mcp lathe --version # images, media and batchuvx --from "lathe-mcp[pdf,ocr]" lathe --version # with PDF and OCRuvx --from "lathe-mcp[pdf,ocr]==0.4.1" lathe --versionpip install "lathe-mcp[pdf,ocr]"[core]working_dir = "/Users/you/Pictures"
[ocr]lang = "eng"
[batch]enabled = true
[privacy]enabled = true{ "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 mcp add lathe -e LATHE_WORKING_DIR=/path/to/your/files -- uvx --from "lathe-mcp[pdf,ocr]" lathe{ "mcpServers": { "lathe": { "command": "uvx", "args": ["--from", "lathe-mcp[pdf,ocr]", "lathe"], "env": { "LATHE_WORKING_DIR": "/path/to/your/files" } } }}{ "servers": { "lathe": { "type": "stdio", "command": "uvx", "args": ["--from", "lathe-mcp[pdf,ocr]", "lathe"], "env": { "LATHE_WORKING_DIR": "/path/to/your/files" } } }}lathe --transport http --port 8765uv venv -p 3.11 .venv && uv pip install -p .venv/bin/python -e '.[dev]'.venv/bin/pytest -qpython3 scripts/check_skills.py.venv/bin/python scripts/tool_lock.py --check.venv/bin/python scripts/security_card.py --check