vvk-charts-mcp
Provides chart generation capabilities using Plotly, including line, bar, pie, scatter, area charts and combined dashboards with customizable themes and export to PNG, SVG, or base64.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vvk-charts-mcp Create a line chart of monthly sales for the last quarter."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vvk-charts-mcp
Documentation language:
English:
README.mdRussian:
README_ru.md
Modern Python MCP server for rendering charts and diagrams (line, bar, pie, scatter, area, and combined dashboard) with customizable themes and export to PNG/SVG/base64.
Table of contents
Related MCP server: mcp-plots
Features
MCP tools for single charts and mixed dashboards.
Terminal chart tools with ANSI rendering and monochrome fallback.
Modern Plotly styling with full theme customization.
Works with multi-series and larger datasets.
Export formats:
png,svg,base64.Interactive CLI test client with predefined templates.
Quick start
Install from GitHub with uvx:
uvx install git+https://github.com/valderan/vvk-charts-mcp.gitRun MCP server:
uvx run vvk-charts-mcpRun interactive test client:
uvx run vvk-charts-cliThe CLI asks what to draw, where to save, output format, and image size.
Tip: set output mode to terminal in vvk-charts-cli to preview console dashboards.
MCP tools
Tool | Purpose |
| Lists available image/terminal themes |
| Trends over time |
| Category comparison |
| Part-to-whole split |
| Correlation and bubble plots |
| Stacked/cumulative composition |
| Multiple chart types in one image |
| ANSI/mono chart output for terminal clients |
| Multi-panel terminal dashboard as plain text |
Common options supported by all tools:
theme_preset,theme,title,width,heightformat(png,svg,base64)filename,save_to_disk
Image tools always return chat preview (ImageContent).
To save files, set save_to_disk: true and configure OUTPUT_DIR in MCP env.
Theme presets
Use list_theme_presets to get all available theme names at runtime.
Image theme presets:
clean_light(default)dark_corporatepastel_startupmedical_monitor
Terminal theme presets:
dark_corporate_cli(default)pastel_startup_cli
Example request:
{
"tool": "list_theme_presets",
"arguments": {}
}Combined dashboard payload example
{
"title": "Marketing Dashboard",
"rows": 1,
"cols": 2,
"theme_preset": "dark_corporate",
"format": "png",
"save_to_disk": true,
"filename": "combined_dashboard",
"panels": [
{
"type": "line",
"row": 1,
"col": 1,
"title": "Revenue Trend",
"x_label": "Month",
"y_label": "k USD",
"data": [
{
"name": "Revenue",
"x": ["Jan", "Feb", "Mar", "Apr"],
"y": [120, 132, 148, 160]
}
],
"options": {
"line_shape": "spline"
}
},
{
"type": "pie",
"row": 1,
"col": 2,
"title": "Budget Split",
"data": [
{
"labels": ["Search", "Social", "Email"],
"values": [45, 35, 20]
}
],
"options": {
"hole": 0.45
}
}
]
}Terminal chart payload example
{
"tool": "create_terminal_chart",
"arguments": {
"type": "line",
"title": "Revenue Trend (CLI)",
"x_label": "Month",
"y_label": "k USD",
"theme": "dark_corporate_cli",
"use_color": true,
"force_mono": false,
"raw_output": true,
"data": [
{
"name": "Revenue",
"x": ["Jan", "Feb", "Mar", "Apr", "May"],
"y": [120, 132, 148, 160, 178]
}
]
}
}raw_output: true is recommended for terminal clients: tool returns only chart text (no JSON wrapper).
Image save behavior (OUTPUT_DIR)
save_to_disk: false(default): no file is written, preview is returned to chat.save_to_disk: trueandOUTPUT_DIRis set: file is saved only intoOUTPUT_DIR.save_to_disk: trueandOUTPUT_DIRis not set: no error, preview only (saved=falsein metadata).output_pathis not supported.
Example MCP config fragment:
{
"mcp": {
"vvkcharts": {
"type": "local",
"enabled": true,
"command": ["uvx", "--from", "git+https://github.com/valderan/vvk-charts-mcp.git", "vvk-charts-mcp"],
"env": {
"OUTPUT_DIR": "./output"
}
}
}
}Demo gallery
AI presets (skill and agent)
Repository includes reusable AI presets in ai/:
ai/vvk-charts-skill.md- skill instructions for chart payload building.ai/vvk-charts-agent.md- chart-specialized subagent profile.
Use whichever workflow is more convenient.
OpenCode setup (detailed)
1) Add this MCP server
Create or edit opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"vvkcharts": {
"type": "local",
"enabled": true,
"command": [
"uvx",
"--from",
"git+https://github.com/valderan/vvk-charts-mcp.git",
"vvk-charts-mcp"
]
}
}
}2) Install as an OpenCode skill
mkdir -p .opencode/skills/vvk-charts-mcp
cp ai/vvk-charts-skill.md .opencode/skills/vvk-charts-mcp/SKILL.md3) Install as an OpenCode agent
mkdir -p .opencode/agents
cp ai/vvk-charts-agent.md .opencode/agents/vvk-charts.md4) Verify
Start
opencodein this repository.Ensure
vvkcharts_*tools are visible.Test prompt:
Build a monthly revenue line chart and save as png in ./output using vvkcharts.
References:
Codex setup (detailed)
Codex-compatible clients may vary, but this flow works in MCP-enabled environments.
1) Register MCP server
uvx --from git+https://github.com/valderan/vvk-charts-mcp.git vvk-charts-mcpTypical JSON shape used by many clients:
{
"mcpServers": {
"vvkcharts": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/valderan/vvk-charts-mcp.git",
"vvk-charts-mcp"
]
}
}
}2) Reuse skill and agent presets
Use
ai/vvk-charts-skill.mdas a reusable prompt template.Use
ai/vvk-charts-agent.mdas a dedicated chart profile/system prompt.
3) Verify
Run a request like:
Use vvkcharts tools to generate a bar chart and save it to ./output/sales-q1.png.
Local development
uv sync
uv run ruff check .
uv run mypy srcRepository
Русская версия документации: README_ru.md
Available Tools
9 toolscreate_area_chartB
Создаёт диаграмму с областями с поддержкой стекинга. Возвращает base64 изображение или путь к файлу.
Inputs: data (required), stack, theme, title, +10 more.
create_bar_chartB
Создаёт столбчатую диаграмму с поддержкой группировки и стекинга. Возвращает base64 изображение или путь к файлу.
Inputs: data (required), theme, title, width, +9 more.
create_combined_dashboardB
Создаёт комбинированный дашборд из нескольких графиков и диаграмм на одном изображении.
Inputs: panels (required), cols, rows, theme, +10 more.
create_line_chartB
Создаёт линейный график с поддержкой множественных серий данных. Возвращает base64 изображение или путь к файлу.
Inputs: data (required), theme, title, width, +9 more.
create_pie_chartB
Создаёт круговую диаграмму с поддержкой doughnut. Возвращает base64 изображение или путь к файлу.
Inputs: data (required), hole, theme, title, +7 more.
create_scatter_chartA
Создаёт точечный график с поддержкой пузырьковых диаграмм. Возвращает base64 изображение или путь к файлу.
Inputs: data (required), theme, title, width, +8 more.
create_terminal_chartC
Рисует график для консоли (ANSI с авто-fallback в монохром).
Inputs: data (required), type (required), theme, title, +8 more.
create_terminal_dashboardC
Рисует текстовый дашборд для консоли из нескольких панелей.
Inputs: panels (required), theme, title, width, +5 more.
list_theme_presetsA
Возвращает список доступных тем для image и terminal графиков, чтобы выбрать тему без чтения документации.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool targets a distinct chart type or output format: line, bar, pie, scatter, area, combined dashboard, terminal chart, and terminal dashboard. The only pair with potential overlap is the two dashboards, but one is explicitly image-based and the other is explicitly terminal-based.
Tool names follow a consistent snake_case verb_noun pattern, with create_*_chart for individual chart types and create_*_dashboard for dashboard variants. The list_theme_presets tool also fits the pattern by using a list verb.
Nine tools is well-scoped for a charting server, covering the main chart types, dashboards, terminal output, and theme discovery. Each tool has a clear responsibility and none feel redundant.
The tool surface covers the major standard chart types, multi-chart dashboards, terminal-specific charts, and theme selection. Since this is a stateless chart-generation server rather than a CRUD system, the absence of update/delete operations is not a gap.
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Bar-first MCP server for Tabula chart authoring, PNG rendering, and editor handoff.
Primarily to be used as a template repository for developing MCP servers with FastMCP in Python, P…
A simple MCP server built with FastMCP and python
Related MCP Servers
- AlicenseAqualityFmaintenanceA Model Context Protocol server that generates lightweight ASCII charts directly in terminal environments, supporting line charts, bar charts, scatter plots, histograms, and sparklines without GUI dependencies.515 npm9MIT
- AlicenseAqualityDmaintenanceA MCP server for data visualization. It exposes tools to render charts (line, bar, pie, scatter, heatmap, etc.) from data and returns plots as either image/text/mermaid diagram.24MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables advanced CSV analysis and data visualization using Google's Gemini AI and Plotly. It allows users to perform exploratory data analysis, generate interactive charts, and conduct complex reasoning on tabular data.32MIT
- AlicenseNot gradedqualityDmaintenanceA modern MCP server that provides interactive graphical user interface, terminal command execution, and AI-powered prompt enhancement for MCP-compatible clients.16 npm7MIT