timeverse-omni-converter-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@timeverse-omni-converter-mcp convert this PDF to a Word document"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Format Converter MCP
Universal format conversion MCP Server
A Model Context Protocol (MCP) server covering full-format conversion across audio, video, images, Office, data, ebooks, PDF, subtitles, and more. It can be called by any MCP client such as TimeVerse Studio, Claude Desktop, Cursor, VS Code, etc.
โจ Features
Feature | Description |
๐ฏ Wide format coverage | 9 format domains, 71 deduplicated formats, plus special capabilities such as subtitles and PDF operations |
๐งฉ 14 tools | 10 core conversion tools + 4 auxiliary tools, precisely categorized by format domain, easy for LLMs to select |
๐ง Smart routing | Automatically selects the optimal conversion path (direct / multi-step chain), auto-degrades when dependencies are unavailable |
๐ง 6 engines | Unified wrapper for FFmpeg / ImageMagick / LibreOffice / Pandoc / Python / PDF |
โก Zero configuration | Auto-detects system dependencies at startup, prompts or degrades when missing |
๐ก๏ธ Production-ready | Tiered error handling, resource limit protection, temp file TTL cleanup |
Related MCP server: GroupDocs.Conversion MCP Server
๐ฆ Supported Formats
Format Domain | Tool | Engine | Format Count | Examples |
Audio |
| FFmpeg | 12 | MP3, WAV, FLAC, AAC, OGG, M4A, WMA, AIFF, OPUS, AC3, AMR, MKA |
Video |
| FFmpeg | 14 | MP4, AVI, MKV, MOV, WebM, FLV, WMV, M4V, MPEG, 3GP, TS, GIF, VOB, RMVB |
Image |
| ImageMagick / Pillow | 16 | JPEG, PNG, GIF, BMP, TIFF, WebP, SVG, HEIC, ICO, PSD, RAW, AVIF, EXR |
Document |
| LibreOffice / Pandoc / pdf2docx | 10 | DOCX, DOC, PDF, RTF, ODT, TXT, PAGES*, WPS*, HTML, MD |
Presentation |
| LibreOffice | 6 | PPTX, PPT, ODP, PDF, KEY*, HTML |
Spreadsheet |
| openpyxl / pandas / LibreOffice | 8 | XLSX, XLS, ODS, CSV, TSV, NUMBERS*, FODS, HTML |
Markup |
| Pandoc | 12 | Markdown, HTML, RST, AsciiDoc, LaTeX, Org, MediaWiki, EPUB, Typst, TXT, IPYNB |
Data |
| Python (PyYAML/tomlkit/pandas/lxml) | 8 | JSON, YAML, XML, TOML, CSV, TSV, Parquet, Protobuf |
Ebook |
| Pandoc / Calibre | 5 | EPUB, MOBI, AZW3, FB2, PDF |
Subtitle |
| pysubs2 | 3 | SRT, ASS/SSA, VTT |
PDF Operations |
| PyMuPDF / pypdf | 9 operations | merge, split, compress, extract, watermark, rotate, to_images |
*marks restricted formats (PAGES / WPS / NUMBERS / KEY), requiring macOS native apps or iCloud export.
Total of approximately 71 formats after deduplication, covering 95%+ of common industry conversion needs.
โ ๏ธ Known Limitations
Restricted formats:
PAGES/WPS/NUMBERS/KEYrequire macOS native apps or iCloud export; they usually cannot be converted directly on other platforms.HEIC/HEIF decoding: Depends on ImageMagick's libheif support; Apple's high-efficiency images cannot be decoded when it is missing.
Engine fallback: If LaTeX is not installed, MarkdownโPDF degrades to weasyprint; if Calibre is not installed, MOBI/AZW3 ebooks are unavailable; if ImageMagick is not installed, image conversion falls back to Python Pillow (with more limited capabilities).
Protocol Buffers: Converting to PB requires an additional
.protodefinition file.Parquet / Protobuf: The corresponding Python dependencies (
pyarrow,protobuf) are optional and must be installed manually.
๐งฐ Tool List
Core Conversion Tools (10)
Tool | Description |
| Audio/video interconversion, audio extraction, clip trimming, subtitle embedding |
| Image interconversion, resizing, optimization, vectorโraster, DPI control |
| High-fidelity Word/PDF/RTF/TXT/HTML/MD conversion, OCR, table extraction |
| PPT/ODP/PDF/HTML/PNG (slide images) conversion |
| Excel/CSV/TSV/JSON/HTML conversion, preserves formulas and multiple worksheets |
| Markdown/HTML/LaTeX/EPUB and other markup text conversion, TOC/highlight/formulas |
| JSON/YAML/XML/TOML/CSV/Parquet/Protobuf data conversion |
| EPUB/MOBI/AZW3/FB2/PDF ebook conversion, cover/metadata |
| PDF merge/split/compress/extract/watermark/rotate/to images |
| SRT/ASS/VTT subtitle interconversion, time offset, encoding conversion |
Auxiliary Tools (4)
Tool | Description |
| Query supported formats, conversion paths, and available engines |
| Probe file metadata (format, encoding, resolution, duration, page count, etc.) |
| Batch conversion, supports Glob matching and parallel execution |
| Check availability and versions of all engines and system dependencies |
All conversion tools uniformly follow the input_path + output_format + options parameter paradigm.
๐๏ธ Architecture
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Client (LLM) โ
โ Claude / Cursor / VS Code / ... โ
โโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ JSON-RPC (stdio)
โโโโโโโโโโโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Protocol Layer โ
โ tool list ยท tool call ยท notifications โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ Tool Router Layer โ
โ ่ฏทๆฑ่งฃๆ โ ๆ ผๅผ่ฏๅซ โ ่ทฏ็ฑๅๅ โ ็ปๆๅฐ่ฃ
โ
โโโโโโโโโโโโโฌโโโโโโโโโโโโฌโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโค
โ Format โ Conversionโ File โ Dependency โ
โ Registry โ Planner โ Manager โ Checker โ
โโโโโโโโโโโโโดโโโโโโโโโโโโดโโโโโโโโโโโดโโโโโโโโโโโโโโโโโโโโค
โ Conversion Engine Layer โ
โ FFmpeg ยท ImageMagick ยท LibreOffice ยท Pandoc โ
โ Python ยท PDF โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโSmart path planning examples:
Source โ Target | Path |
PDF โ XLSX | PDF โ CSV (pdfplumber) โ XLSX (openpyxl) |
PDF โ DOCX | PDF โ DOCX (pdf2docx) |
XLSX โ JSON | XLSX โ DataFrame (pandas) โ JSON |
PPTX โ MD | PPTX โ HTML (LibreOffice) โ MD (Pandoc) |
DOCX โ EPUB | DOCX โ HTML (Pandoc) โ EPUB (Pandoc) |
โ๏ธ Tech Stack
Primary language: TypeScript (Node.js โฅ 18)
Protocol:
@modelcontextprotocol/sdkConversion engines: FFmpeg / ImageMagick / LibreOffice / Pandoc / Python (venv isolated) / PyMuPDF
System Dependencies
Dependency | Version | Purpose | Installation |
Node.js | โฅ 18 | Run MCP Server | |
FFmpeg | โฅ 6.0 | Audio/video/subtitle conversion |
|
ImageMagick | โฅ 7.0 | Image conversion |
|
LibreOffice | โฅ 7.5 | High-fidelity Office document conversion | |
Pandoc | โฅ 3.0 | Markup/document/ebook conversion |
|
Python | โฅ 3.10 | Data/PDF/spreadsheet/subtitle |
LaTeX (optional, high-quality MarkdownโPDF) and Calibre (optional, MOBI/AZW3) can be omitted; the system will automatically degrade.
Python Dependencies
pip install -r python/requirements.txtCore dependencies: openpyxl, pandas, PyYAML, tomlkit, xmltodict, PyMuPDF, pypdf, pdf2docx, pysubs2, Pillow (pyarrow, protobuf are optional).
๐ Installation
First install the system dependencies (FFmpeg / ImageMagick / LibreOffice / Pandoc):
Windows:
npm run prepare-deps(one-click download of portable versions)macOS:
brew install ffmpeg imagemagick pandoc && brew install --cask libreofficeLinux:
apt install ffmpeg imagemagick libreoffice pandoc
Then build and install the Python dependencies:
# 1. ๅฎ่ฃ
Node ไพ่ต
npm install
# 2. ๆๅปบ๏ผ็ๆ dist/๏ผ
npm run build
# 3. ๅฎ่ฃ
Python ไพ่ต๏ผๅปบ่ฎฎไฝฟ็จ่ๆ็ฏๅข๏ผ
python3 -m venv .venv # macOS/Linux๏ผWindows ไฝฟ็จ python
source .venv/bin/activate # macOS/Linux๏ผWindows ไฝฟ็จ .venv\Scripts\activate
pip install -r python/requirements.txt๐ MCP Configuration
Add the following server to the mcpServers configuration of your MCP client.
TimeVerse Studio (Recommended ยท npm hosted)
TimeVerse Studio uses the standard mcpServers JSON integration. After publishing to npm, run it directly via npx with one command โ no local build required:
{
"mcpServers": {
"timeverse-omni-converter-mcp": {
"command": "npx",
"args": ["-y", "timeverse-omni-converter-mcp"],
"env": {
"FC_PYTHON_PATH": "python",
"FC_TEMP_DIR": "C:/temp/format-converter",
"FC_MAX_FILE_SIZE": "524288000",
"FC_TIMEOUT": "300000"
}
}
}
}Claude Desktop / Cursor (local build)
After building locally, run directly via node:
{
"mcpServers": {
"timeverse-omni-converter-mcp": {
"command": "node",
"args": ["C:/path/to/timeverse-omni-converter-mcp/dist/index.js"],
"env": {
"FC_PYTHON_PATH": "python",
"FC_TEMP_DIR": "C:/temp/format-converter",
"FC_MAX_FILE_SIZE": "524288000",
"FC_TIMEOUT": "300000"
}
}
}
}macOS: change
argsto/Users/<you>/timeverse-omni-converter-mcp/dist/index.js, and changeFC_PYTHON_PATHtopython3(or remove the entry to let it auto-detect.venv/python3).
๐ง Environment Variables
Variable | Default | Description |
|
| Python interpreter path |
|
| FFmpeg executable path |
|
| ffprobe executable path |
|
| ImageMagick executable path |
|
| LibreOffice executable path |
|
| Pandoc executable path |
|
| Calibre ebook converter path |
| System temp directory | Temporary file directory |
|
| Maximum input file size |
|
| Total extracted size limit (anti zip bomb) |
|
| Maximum compression ratio |
|
| Image decompression pixel limit (anti decompression bomb) |
|
| Single conversion timeout |
|
| Default parallelism |
|
| Log level |
๐ฌ Usage Examples
Give natural language instructions to the LLM in your MCP client, for example:
"Convert
a.movtoa.mp4, resolution 1920x1080" โconvert_media"Convert
photo.heictophoto.png" โconvert_image"Convert
report.docxtoreport.pdf" โconvert_document"Convert
data.jsontodata.csv" โconvert_data"Export every page of
slides.pptxas PNG" โconvert_presentation"Convert
book.epubtobook.mobi" โconvert_ebook"Merge
a.pdfandb.pdf" โconvert_pdf(operation: "merge")"Convert
subs.asstosubs.srt" โconvert_subtitle
Tool call example:
{
"name": "convert_media",
"arguments": {
"input_path": "C:/media/input.mov",
"output_format": "mp4",
"options": {
"video_codec": "libx264",
"video_resolution": "1920x1080",
"crf": 23
}
}
}Returned result:
{
"success": true,
"outputPath": "C:/media/input.mp4",
"outputSize": 10485760,
"duration": 3215,
"warnings": []
}โ FAQ
Q: What should I do if conversion reports missing dependencies or fails?
A: Call the check_dependencies tool to view the availability status and versions of each engine (FFmpeg / ImageMagick / LibreOffice / Pandoc / Python), install the missing dependencies, and retry.
Q: Python-related conversions (data / PDF / spreadsheet / subtitle) report errors?
A: Make sure the dependencies have been installed via pip install -r python/requirements.txt, and point FC_PYTHON_PATH to the correct Python interpreter (or an activated virtual environment).
Q: What happens if the target file already exists?
A: By default it is automatically renamed to filename_1.extension; for batch conversion, the on_conflict parameter can control overwrite / skip / rename.
Q: Why can't certain formats (such as PAGES / NUMBERS) be converted? A: These are Apple proprietary formats that require macOS native apps or iCloud export. They are restricted formats โ see "Known Limitations" for details.
Q: What should I do if large file conversion times out?
A: Increase FC_TIMEOUT (default 300000ms), and note the FC_MAX_FILE_SIZE (default 500MB) limit.
๐ก๏ธ Security
The server processes untrusted file content and has multiple built-in resource and security protections:
Input file size, extracted volume, compression ratio, and image pixel limits (anti zip bomb / decompression bomb)
Per-conversion timeout and concurrency limits
Parsers disable XXE (external entity injection), PDF embedded scripts, and external resource loading
External processes are uniformly invoked with argument arrays (
execFile) to avoid command injection
๐ License
MIT
Available Tools
14 toolsbatch_convertB
ๆน้่ฝฌๆขๅคไธชๆไปถ๏ผๆฏๆ Glob ๆจกๅผๅน้ ไธๅนถ่กๆง่กใ
Inputs: output_format (required), options, parallel, output_dir, +3 more.
check_dependenciesA
ๆฃๆฅๆๆ่ฝฌๆขๅผๆไธ็ณป็ปไพ่ต็ๅฏ็จๆงไธ็ๆฌใ
Inputs: no named parameters.
convert_dataB
็ปๆๅๆฐๆฎ่ฝฌๆข๏ผJSON/YAML/XML/TOML/CSV/TSV/Parquet/Protocol Buffers๏ผPB ้ .proto ๅฎไน๏ผใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_documentB
ๆๆกฃ่ฝฌๆข๏ผDOCX/DOC/PDF/RTF/ODT/TXT/HTML/MD๏ผ้ซไฟ็ไฟ็ๆ็ใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_ebookB
็ตๅญไนฆ่ฝฌๆข๏ผEPUB/MOBI/AZW3/FB2/PDF/TXT/HTML/DOCX๏ผไฟ็็ซ ่ใๅ ๆฐๆฎไธๅฐ้ขใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_imageB
ๅพ็ๆ ผๅผไบ่ฝฌ๏ผๆฏๆ JPEG/PNG/GIF/BMP/TIFF/WebP/SVG/HEIC/ICO/AVIF/PSD/RAW ็ญ๏ผๅฏ็ผฉๆพใไผๅใๆงๅถ DPIใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_markupC
ๆ ่ฎฐ/ๆๆฌ่ฝฌๆข๏ผMarkdown/HTML/reStructuredText/AsciiDoc/LaTeX/Org/MediaWiki/EPUB/Typst/็บฏๆๆฌ/Jupyterใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_mediaA
้ณ้ข/่ง้ขๆ ผๅผไบ่ฝฌ๏ผๆฏๆ MP3/WAV/FLAC/AAC/OGG/M4A/MP4/MKV/AVI/MOV/WebM/FLV/WMV ็ญ๏ผๅฏๆๅ้ณ้ขใๆชๅ็ๆฎตใๅตๅ ฅๅญๅนใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_pdfB
PDF ไธ็จๆไฝ๏ผmerge/split/compress/extract_pages/extract_text/extract_images/add_watermark/rotate/to_imagesใ
Inputs: operation (required), options, input_path, input_paths, +1 more.
convert_presentationB
ๆผ็คบๆ็จฟ่ฝฌๆข๏ผPPTX/PPT/ODP/PDF/HTML/PNG๏ผๅนป็ฏ็ๅพ็๏ผใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_spreadsheetB
็ตๅญ่กจๆ ผ่ฝฌๆข๏ผXLSX/XLS/ODS/CSV/TSV/JSON/HTML๏ผไฟ็ๅ ฌๅผใๆ ทๅผไธๅคๅทฅไฝ่กจใ
Inputs: input_path (required), output_format (required), options, output_path.
convert_subtitleC
ๅญๅนๆ ผๅผ่ฝฌๆข๏ผSRT/ASS/SSA/VTT๏ผๆฏๆ็ผ็ ่ฝฌๆขไธๆถ้ดๅ็งปใ
Inputs: input_path (required), output_format (required), options, output_path.
get_file_infoA
ๆขๆตๆไปถๅ ไฟกๆฏ๏ผๆ ผๅผใ็ผ็ ใๅ่พจ็ใๆถ้ฟใ็ ็ใ้กตๆฐใๅทฅไฝ่กจๆฐ็ญใ
Inputs: file_path (required), include_checksum.
get_supported_formatsA
ๆฅ่ฏขๆฏๆ็ๆ ผๅผใ่ฝฌๆข่ทฏๅพไธๅฏ็จๅผๆ๏ผๅฏๆๅ็ฑป่ฟๆปคใ
Inputs: format, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 14 tools
ๆฏไธช่ฝฌๆขๅทฅๅ ท้ๅฏน็นๅฎๅชไฝ็ฑปๅ๏ผๅชไฝใๅพๅใๆๆกฃใๆผ็คบใ็ตๅญ่กจๆ ผใๆ ่ฎฐใๆฐๆฎใ็ตๅญไนฆใPDFใๅญๅน๏ผ๏ผ็จ้ๆ็กฎไธ้ๅ ใ่พ ๅฉๅทฅๅ ทๅฆ่ทๅๆฏๆๆ ผๅผใๆไปถไฟกๆฏใๆน้่ฝฌๆขๅไพ่ตๆฃๆฅไธ่ฝฌๆขๅทฅๅ ทๅบๅๆๆพใ
ๆๆๅทฅๅ ทๅ็งฐๅ้็จไธ่ด็ๅจ่ฏ_ๅ่ฏๆจกๅผ๏ผๅฆconvert_mediaใget_file_infoใbatch_convert๏ผ๏ผๅ จ้จไฝฟ็จๅฐๅ่ๅฝขๅฝๅๆณ๏ผ้ฃๆ ผ็ปไธ๏ผๆไบ้ขๆตๅ้ๆฉใ
14ไธชๅทฅๅ ท่ฆ็ไบๅนฟๆณ็่ฝฌๆข้ขๅ๏ผๆฏไธชๅทฅๅ ท้ฝ้ๅฏน็นๅฎ็ๆ ผๅผ็ฑปๅซๆ่พ ๅฉๅ่ฝ๏ผๆฐ้้ไธญ๏ผๆฒกๆๅไฝๆๆๆพไธ่ถณ๏ผไธๆๅกๅจ็ฎ็ๅน้ ใ
ๅทฅๅ ท้่ฆ็ไบๅชไฝใๅพๅใๆๆกฃใๆผ็คบใ็ตๅญ่กจๆ ผใๆ ่ฎฐใๆฐๆฎใ็ตๅญไนฆใPDFๅๅญๅน็ญๅค็งๆ ผๅผ่ฝฌๆข๏ผๅนถๅ ๅซๆ ผๅผๆฅ่ฏขใๆไปถไฟกๆฏใๆน้่ฝฌๆขๅไพ่ตๆฃๆฅ็ญ่พ ๅฉๅ่ฝ๏ผ็ไผผๅฎๆดๆ ้ๅคง็ผบๅคฑใ
Maintenance
Related MCP Connectors
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
FFmpeg processing for video, audio and images via MCP with OAuth and shared account allowance.
Convert images to PNG, JPEG, WebP, or AVIF through one public remote MCP tool.
Preflight and convert 450+ file types for AI via TweekIT MCP & SDK (Cloud CGN or On-Prem Miner).
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables file conversion between 690+ formats (image, video, audio, document, data, font, ebook, archive) using an MCP server, with no API key or signup required.26MIT
- AlicenseNot gradedqualityBmaintenanceEnables local document conversion between 70+ formats (PDF, Word, Excel, etc.) via MCP, keeping files private.MIT
- AlicenseNot gradedqualityBmaintenanceEnables document conversion and processing through MCP, including Office/PDF/Markdown conversions, OCR, and PDF operations like split, rotate, encrypt, and extract.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to convert and process various document formats through an MCP server interface.-