io.github.HelgDemidov/refigure is an MCP server that convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures. Its tool list has not been published yet over stdio, requires no API key, and scores 54/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-helgdemidov-refigure": {
"command": "uvx",
"args": [
"refigure"
]
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'refigure' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked refigure against OSV.dev.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationBe the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in writing / data
Manage Supabase projects — databases, auth, storage, and edge functions
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
MCP server for document format conversion using pandoc.
DataForSEO API modelcontextprotocol server
MCP Security Weekly
Get CVE alerts and security updates for io.github.HelgDemidov/refigure and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Converters where figures survive.
DOCX/XLSX → Markdown that keeps charts and infographics machine-readable
instead of losing them to OCR or a vision model: native OOXML chart data
(numCache/strCache) recovers exact numbers with zero GPU calls, zero
VLM calls, zero lost precision — by default, not as a fallback.
That default path is also why the base install (pip install "refigure[docx,xlsx]") is ~500x lighter than PyTorch-based
alternatives (5.6MB vs. multi-GB) — the core conversion needs no ML
model at all. That number is about the core architecture, not every
distribution format: the Docker image trades it back deliberately,
bundling VLM providers + LibreOffice for a turnkey composite-figure path
(see Docker below).
VLM interpretation itself is there for the rare figure with no native data at all (a dashboard screenshot) — never required just to get real numbers out of a chart, on any distribution format.
Ships as a library, CLI, MCP server, and a one-click Claude Desktop bundle — every surface returns the same native-fidelity output, not a degraded summary for agents.
numCache/strCache
directly; no rasterize/OCR/VLM step for charts, real numbers every time.[vlm] extra,
--vlm/Config(use_vlm=True)) — cloud description + a real rendered
mermaid diagram (26 supported diagram types — flowcharts, pie/xy charts,
sequence/state/ER diagrams, Gantt/timeline/sankey/treemap and more, see
Status below) on top of the zero-loss floor, for figures with no native
chart data at all (e.g. a dashboard screenshot). Provider-agnostic —
OpenRouter by default, or direct OpenAI/Ollama/vLLM/LM Studio/Anthropic
via --vlm-provider ([vlm-direct] extra). --strict upgrades one
specific failure (the system soffice/LibreOffice binary missing) from
a graceful skip to a hard error; every other VLM failure still degrades.ConversionResult (markdown + warnings +
chart/group counts + vlm_used), not a bare string.refigure console command, stdin/stdout-first, native
batch mode, typed exit codes (see below).refigure-mcp console command ([mcp] extra),
stdio or Streamable HTTP, tools/resources/prompts, batch conve