Vizdown-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| render_diagramA | Render the first diagram found in a Markdown file or raw text. Args: file_path: Path to a .md file containing a diagram block. raw_markdown: Raw markdown string with a diagram code block. output_format: "svg" (default), "png", "jpeg", or "pdf". theme: "light" (default) or "dark". look: "default" or "handDrawn" (Mermaid sketch mode). scale: Resolution multiplier for PNG/JPEG (default 2). Returns: Dict with diagram_type, output_format, and base64-encoded output. |
| render_all_diagramsA | Render ALL diagram blocks found in a Markdown file. Parses the entire document, finds every diagram block, renders each separately, and optionally saves output files. Args: file_path: Path to a .md file. raw_markdown: Raw markdown string. output_format: "svg", "png", "jpeg", or "pdf". theme: "light" or "dark". look: "default" or "handDrawn". scale: Resolution multiplier for raster output. output_dir: Directory to save rendered files. Files are named {stem}{type}{index}.{format}. Returns: List of result dicts, each with diagram_type, index, and base64 output. |
| list_diagramsA | List all detected diagram blocks without rendering them. Args: file_path: Path to a .md file. raw_markdown: Raw markdown string. Returns: List of dicts with diagram_type, line_start, and line_end for each block. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools have overlapping purposes that could cause confusion: 'render_all_diagrams' and 'render_diagram' both render diagrams with similar parameters, differing only in whether they process all diagrams or just the first one. 'list_diagrams' is distinct for listing without rendering, but the two render tools have unclear boundaries that might lead to misselection.
All tool names follow a consistent snake_case pattern with clear verb_noun structure: 'list_diagrams', 'render_all_diagrams', and 'render_diagram'. The naming is predictable and readable throughout the set.
Three tools is a reasonable count for a diagram rendering server, allowing for listing and rendering operations. It's slightly thin but covers core functionality without being excessive for the apparent scope.
The tool set covers listing and rendering diagrams with various output options, but there are notable gaps: no tools for updating, deleting, or managing diagram content directly (e.g., editing or validating diagrams), which limits lifecycle coverage for the domain.