Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MarcSkovMadsen/holoviz-mcp --skill holoviz-mcp-cligit clone --depth 1 https://github.com/MarcSkovMadsen/holoviz-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/marcskovmadsen/holoviz-mcp/holoviz-mcp-cli)<a href="https://agentmods.dev/skills/marcskovmadsen/holoviz-mcp/holoviz-mcp-cli"><img src="https://agentmods.dev/badge/skills/marcskovmadsen/holoviz-mcp/holoviz-mcp-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marcskovmadsen/holoviz-mcp/holoviz-mcp-cli"><img src="https://agentmods.dev/badge/skills/marcskovmadsen/holoviz-mcp/holoviz-mcp-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01268 |
| Opus 5 | $0.00023 | $0.00634 |
| Sonnet 5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
holoviz-mcp-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
holoviz-mcp CLI
The holoviz-mcp CLI provides direct access to HoloViz documentation, component introspection, and visualization tools from the command line.
Installation
The recommended way to install is as a uv tool:
uv tool install holoviz-mcp
This installs both holoviz-mcp and hv commands into an isolated environment. Use hv as a shorter alternative in all examples below (e.g., hv search Panel Tabulator, hv pn get Button).
When to Use CLI vs MCP
- Prefer MCP tools when the HoloViz MCP server is loaded — they return structured, typed data (including images) and integrate natively with LLM tool calling
- Use CLI when MCP tools are not available but
holoviz-mcp(orhv) is installed and you have Bash/shell access - Search the web as a last resort when neither MCP tools nor CLI are available
Output Formats
All tool commands support three output formats via --output / -o:
pretty(default) — Rich terminal output with colors and tables, for humansmarkdown— Markdown-formatted text, optimized for LLMsjson— Structured JSON, for scripts and programmatic use
Setup commands (serve, install, update) output human-readable text by default.
Command Structure
Commands follow noun-verb pattern with Python import aliases for library-specific tools:
holoviz-mcp <command> # general tools
holoviz-mcp pn <command> # Panel tools (import panel as pn)
holoviz-mcp hv <command> # HoloViews tools (import holoviews as hv)
holoviz-mcp hvplot <command> # hvPlot tools (import hvplot)
Quick Reference
Search & Documentation
holoviz-mcp search Panel Tabulator # search all indexed docs (no quotes needed)
holoviz-mcp search query -p panel # search within a project
holoviz-mcp search query -n 5 # return up to 5 results
holoviz-mcp doc get <path> <project> # get specific document (use search to find paths)
holoviz-mcp ref get <component> # find reference guide (when you know the exact name)
holoviz-mcp ref get <component> -p panel # filter by project
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 113 lines · 47 tokens per session scan A fb7e5178ff40
holoviz-mcp-cli is a skill published in the GitHub repository MarcSkovMadsen/holoviz-mcp (34 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 47 tokens to every session and 1,268 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dataviz-mcp
Show Python visualizations live in the browser with the dataviz-mcp MCP tools (show, screenshot). Use when those tools are available and the user asks to display, plot, chart, or visualize anything. Do not use for apps the user serves themselves with panel serve.
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…
portaljs-add-map
Render a GeoJSON dataset on an interactive Leaflet map in the Views section of a dataset's showcase. Installs react-leaflet and a Map component, then renders the map for the chosen dataset. Use when a dataset's data is geographic and a map view is needed alongside the showcase's default metadata and download.
portaljs-add-chart
Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal. Installs recharts, writes a reusable Chart component, and renders it in the showcase Views section. Use when visualizing a dataset already registered in datasets.json.
malloy-html-data-apps
Build or modify an in-package HTML data app for a Malloy Publisher package (a public/ directory the package serves). Use when the user wants a hand-authored HTML dashboard or web page backed by a package's Malloy models, with no build step.
reimagine-it-extract
Emit the content signals reimagine-it reads from an HTML file — title, anchors, proper nouns, dates, numbers, emails, links, source hex colors, and the derived palette — as JSON without generating a redesign. Use when the user says /reimagine-it extract, "what does the engine see in this page", "extract the palette"…