MCP server for interactive data visualisation — bar, pie, line, doughnut, radar, polar, and area charts
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"chuk-mcp-chart","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Chuk MCP Chart **Interactive data visualisation via MCP** — paste a CSV, describe your data, ask for a chart. Bar, pie, line, doughnut, radar, polar, and area charts rendered instantly. > This is a demonstration project provided as-is for learning and testing purposes. [](https://www.python.org/downloads/) ## Features Three tools that turn raw data into beautiful charts: ### 1. Show Chart (`show_chart`) Create a chart from explicit data. Provide labels, one or more datasets, and optional configuration: - **Chart types**: bar, line, pie, doughnut, radar, polar, area - Axis labels, legend position, stacked mode - Custom colours per dataset - Auto-assigned colour-blind-friendly palette ### 2. Chart from CSV (`chart_from_csv`) Paste raw CSV text and get a chart — zero configuration required: - First non-numeric column becomes category labels - Every numeric column becomes a dataset (series) - If all columns are numeric, row numbers are used as labels - Perfect for spreadsheet data ### 3. Chart from JSON (`chart_from_json`) Pass a JSON array of objects and get a chart automatically: - First string field becomes category labels - Every numeric field becomes a dataset - Great for API responses or structured data ## Installation ### Using uvx (Recommended - No Installation Required!) ```bash uvx chuk-mcp-chart ``` This automatically downloads and runs the latest version. Perfect for Claude Desktop! ### Using uv (Recommended for Development) ```bash # Install from PyPI uv pip install chuk-mcp-chart # Or clone and install from source git clone https://github.com/IBM/chuk-mcp-chart.git cd chuk-mcp-chart uv sync --dev ``` ### Using pip (Traditional) ```bash pip install chuk-mcp-chart ``` ## Usage ### With Claude Desktop #### Option 1: Run Locally with uvx ```json { "mcpServers": { "chart": { "command": "uvx", "args": ["chuk-mcp-chart"] } } } ``` #### Option …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.