Darwin-owned Files
Server Details
Free offline file conversions and bounded DOCX text extraction. Supplied bytes; no network.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool targets a distinct source format and output format or operation, so an agent can select the right one without overlap. The only apparent pair, csv_to_xlsx and xlsx_to_csv, is clearly directional and not confusable.
All names use snake_case and mostly follow a source_to_target pattern, which is predictable and readable. zip_text_files and event_brief_to_ics deviate slightly from that pattern but remain clear and consistent in style.
Six tools is well scoped for a focused file-conversion server, and each tool covers a distinct conversion task. There are no redundant or obviously unnecessary tools.
The surface covers several useful conversions, including CSV/XLSX both ways, DOCX extraction, Markdown-to-PDF, ICS creation, and text zipping. However, common counterparts such as PDF-to-text, text-to-DOCX, unzip, and general file read/write operations are missing, creating notable dead ends for a general file toolkit.
Available Tools
6 toolscsv_to_xlsxARead-onlyIdempotentInspect
Convert exact caller CSV to a real XLSX spreadsheet with one Data sheet and a SUM totals row. Explicit numericColumns and totalColumns; all other cells are literal strings, never inferred formulas. Returns actual file bytes. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: csv (required), totalColumns (required), numericColumns (required). Returns: artifacts, sheetNames, sourceSha256, externalWrites
docx_to_textARead-onlyIdempotentInspect
Extract complete text from caller-supplied canonical base64 DOCX bytes using the bounded Creora document parser. Returns actual text, source/text SHA256 and ordered document parts. No URL or file lookup, network, OCR, PDF, macros, field evaluation or external writes. Refuses unsupported or over-budget documents instead of truncating. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: documentBase64 (required), contractVersion, includeHeadersFooters. Returns: Whole actual extracted text and hashes; no stored or inferred result.
event_brief_to_icsARead-onlyIdempotentInspect
Create a real iCalendar file from a brief with Start: YYYY-MM-DD HH:MM IANA/Zone, Duration: N minutes, Title: text, optionally preceded by a Markdown heading. Resolves timezone to UTC; refuses ambiguous/nonexistent DST times. createdAt must be UTC ISO seconds. Does not add any calendar event. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: createdAt (required), eventBrief (required). Returns: artifacts, sheetNames, sourceSha256, externalWrites
markdown_to_pdfARead-onlyIdempotentInspect
Render caller-supplied text Markdown to a real downloadable PDF. Headings, paragraphs and lists; Windows-1252 text only. No images, HTML, fetches or external writes. Returns actual inline file bytes and SHA256. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: markdown (required). Returns: artifacts, sheetNames, sourceSha256, externalWrites
xlsx_to_csvARead-onlyIdempotentInspect
Extract every sheet from a caller-supplied base64 XLSX into separate genuine UTF-8 CSV files, preserving sheet names in metadata and cell values. Formula values require existing caches; does not execute formulas. Refuses macros, external links and expansion bombs. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: xlsxBase64 (required). Returns: artifacts, sheetNames, sourceSha256, externalWrites
zip_text_filesARead-onlyIdempotentInspect
Create an exact ZIP of caller-supplied named UTF-8 texts. Preserves bytes and nested safe paths; rejects traversal, duplicate/colliding names and excessive data. No external files or fetches. Official documentation: https://creora.darwin.so/providers/files/docs
Inputs: files (required). Returns: artifacts, sheetNames, sourceSha256, externalWrites
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Convert files too big or exotic for a sandbox: 140+ formats, batch, OCR, AI extraction, TTS/STT
Convert DOCX documents to and from PDF, TXT, HTML, ODT, JPG and RTF.
Convert files and authorized public HTTPS pages to text, editable Word or Markdown.
Convert PDF, DOCX, XLSX and 25 other formats to clean Markdown for LLMs and RAG. No key or account.
Related MCP Servers
- FlicenseBqualityBmaintenanceEnables local, offline document extraction and manipulation—PDF first but also HTML, DOCX, XLSX, PPTX, EML, EPUB, Markdown, and plain text—through tools for probing, locating, extracting, converting, assembling, OCR, protecting, and redacting documents, with nothing leaving the machine.7-
- AlicenseAqualityBmaintenanceLocal, offline conversion of PDFs, Office files (DOCX,XLSX,PPTX), XML, and screenshots into compact Markdawn for LLM and RAG. Removes repeated headers, footers, page numbers, hidden text and tracking links, records every removal with its reason, and marks unreadable text instead of guessing, Reads only the folders you allow; no networks, no telemetry2AGPL 3.0
- AlicenseAqualityBmaintenanceConverts local PDF, Word, Excel and PowerPoint files into token-lean Markdown for LLMs, reporting the tokens saved and paging large documents. Runs entirely on your machine: no uploads, no API keys.3619 npmApache 2.0
- AlicenseAqualityBmaintenanceConverts documents to clean Markdown for AI agents from a URL or base64 — no API key, built for remote hosting. Supports PDF (tables preserved as Markdown/CSV/JSON), DOCX, PPTX, XLSX, EPUB, HTML and CSV; scanned PDFs and images go through offline OCR. Includes full-text search, page-range reading, metadata inspection, PDF split/merge and image export, with SSRF-protected fetching, 30 MB limits and10AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.