rayomd-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --root | No | Folder the server may read from and write to. Repeatable; relative paths resolve from the first root. Default: the working folder. Strongly recommended so the server does not use a client-chosen working directory. | |
| --timeout | No | Timeout in seconds for a rayomd call. Default: 60. | |
| --workers | No | Maximum number of rayomd worker processes. Default: one per CPU, at most 4. | |
| RAYOMD_FONT | No | Font read by rayomd itself for characters missing from the default font. | |
| RAYOMD_PATH | No | Path to the rayomd executable. If unset, rayomd is found on PATH or a pinned release is downloaded. | |
| LOCALAPPDATA | No | Base cache directory where the downloaded rayomd binary is kept on Windows. | |
| --allow-theme | No | Allow theme files. The theme file itself is checked against the roots. Disabled by default. | |
| XDG_CACHE_HOME | No | Base cache directory where the downloaded rayomd binary is kept on Linux. | |
| RAYOMD_GUI_PATH | No | Path to the RayoMD GUI executable used by open_in_gui. If unset, rayomd-gui is found on PATH. | |
| --allow-url-images | No | Enable URL images in Markdown. Without this flag, URL images are not allowed and the corresponding tool option is not exposed. | |
| --allow-embed-source | No | Allow embedded sources, needed for recover_markdown to create PDFs with embedded Markdown. Disabled by default. | |
| RAYOMD_FALLBACK_FONT | No | Fallback font read by rayomd itself for missing characters and PDF/A. | |
| --allow-unsafe-local-images | No | Allow local images from anywhere, not only from the Markdown file's folder. Disabled by default. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| markdown_to_pdfA | Converts Markdown (text or a file) to a PDF with RayoMD and returns the PDF's page count and warnings. Renders: GitHub Markdown (tables, task lists, footnotes, alerts > [!NOTE]), PNG/JPEG/SVG images with alt text (relative paths inside the Markdown file's folder), TeX math ($...$, $$...$$ on own lines, |
| book_to_pdfA | Makes one PDF of several Markdown files: each from a new page, links between them kept, one outline (and with toc one table of contents). The files a SUMMARY.md lists or a folder holds must lie in that folder. |
| recover_markdownA | Gets back the exact Markdown source of a reversible PDF (one exported with the source embedded), checked against its digest. Returns the text, or writes it to a new .md file; the PDF is not changed. |
| open_in_guiA | Opens a Markdown file in RayoMD GUI, the desktop editor with a live PDF preview, for the user to read or edit. The GUI checks the file about once a second, focused or not, and reloads it when it changed on disk and its buffer has no unsaved edits, so a file the agent rewrites shows the new version. Needs RayoMD GUI installed (rayomd-gui on PATH or RAYOMD_GUI_PATH) and a desktop session (Wayland on Linux). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| syntax | What RayoMD renders (GitHub Markdown, alerts, footnotes, math, Mermaid, code colours) and what degrades |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: single-file conversion, multi-file book conversion, source recovery, and GUI opening. The descriptions explicitly clarify boundaries, especially between markdown_to_pdf and book_to_pdf.
Names are all snake_case and descriptive, but the convention mixes source_to_target names (markdown_to_pdf, book_to_pdf) with verb_object names (recover_markdown, open_in_gui). The pattern is still readable and logical.
Four tools are well-scoped for a Markdown-to-PDF conversion server. Each tool covers a distinct workflow without unnecessary surface area.
The surface covers the core lifecycle: convert a single Markdown file, convert a multi-file book, recover embedded Markdown from reversible PDFs, and open files in the GUI for preview/editing. No obvious dead ends for the stated purpose.