mcpField
C
Chart Color System

Chart Color System

Remote
socraticstatic.github.ioMedia & Design0Updated 3w ago

About Chart Color System

Chart Color System is a read-only MCP server exposing the Chart Color System engine for palette solving, auditing, simulation, and ramp generation. It is intended for assistants that need measured chart-color results.

Key features

  1. 01Solve anchored categorical palettes
  2. 02Audit palettes with pass, warn, or fail results
  3. 03Simulate four vision modes
  4. 04Build sequential or diverging ramps
  5. 05Report the engine version in results

Use cases

  1. 01Generate an anchored chart palette
  2. 02Check palette findings with measurements
  3. 03Preview colors under vision simulations
  4. 04Create sequential or diverging color ramps

MCP support

The server exposes `solve_palette`, `audit_palette`, `simulate_palette`, and `build_ramp` to MCP clients. It reports the engine version in each result.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://chart-color-mcp.vercel.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

4
ParameterTypeRequiredDescription
nintegerNoNumber of categorical slots
gridstringNoGridline color; defaults to a light or dark gray to match the background
anchorsarrayNoBrand or required colors, kept exactly, in slot order (CSS syntax)
postureenumNokpi: few strong colors; comparative: balanced; exploratory: many mutedkpi | comparative | exploratory
backgroundstringNoChart background color

Details

From the project README

chart-color-mcp

The Chart Color System as a read-only MCP server: the same engine as the app (npm chart-color-system), callable by any assistant. The app is static on GitHub Pages, so this directory is its own Vercel project (chart-color-mcp, team socraticstatics-projects), deployed from here, not from the Pages workflow.

  • Endpoint: https://chart-color-mcp.vercel.app/mcp
  • Docs for humans and assistants: https://socraticstatic.github.io/Visualizations/mcp-docs.html (source: public/mcp-docs.html)
  • Tools: solve_palette (anchored, audited categorical palette), audit_palette (pass / warn / fail with the numbers), simulate_palette (deutan, protan, tritan, achromatopsia), build_ramp (sequential or diverging)
  • Engine version is reported in every result (engine_version); bump the chart-color-system dependency to ship a new engine.

Deploy and verify:

cd mcp && npm run deploy && npm test

npm test runs the contract tests against production plus the local card and handler tests; MCP_BASE=<preview url> npm test runs the contract tests against a preview deployment.

Release to the MCP Registry (io.github.socraticstatic/chart-color-system): bump version in server.json and package.json (one number, the server reports it), deploy, then tag mcp-v<version> and push the tag. .github/workflows/publish-mcp.yml publishes over GitHub OIDC and refuses a tag that disagrees with the card or with what the live server reports.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.