Minipainter MCP Server

Local-first miniature-paint inventory and cross-brand color matching for AI agents.

Remote serverstreamable-http

What is the Minipainter MCP server?

Local-first miniature-paint inventory and cross-brand color matching for AI agents. That is what the minipainter mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

minipainter is a local-first paint registry for miniature-painting workflows. It exists for one practical reason: AI paint suggestions are much more useful when they understand the paints you actually own.

  • keep a local record of what is in your paint rack
  • search it quickly by name, role, family, and approximate color
  • prepare a stable inventory foundation for a future AI skill that can inspect links, photos, and model images

The tools it exposes

The server publishes 14 tools. What each one is for:

  • owned — first paint lookup and cross-brand color matching
  • Owned — first matching: lookups and recommendations can prioritize paints you already have
  • RGB — aware search: approximate RGB values help with nearest-color matching
  • Agent — friendly CLI: deterministic command output for AI integration (Claude + ChatGPT MCP)
  • POSIX — ish shell (Linux, macOS, WSL)
  • Self — hosted HTTP server** — a single Docker-friendly runtime with JSON storage and API endpoints
  • toggle — quit
  • image — driven inventory fill from paint bottle photos
  • model — photo analysis that recommends owned paints first
  • Built — in catalog data lives in data/catalog/ (Citadel and Army Painter, kept in version control)
  • paint_search — paint_show
  • inventory_list — inventory_mark_owned

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

What it needs from you

Configuration is passed through the environment: INVENTORY_SYNC_TOKEN, PORT, INVENTORY_PATH, DATABASE_URL, AUTH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Minipainter's toolset — owned, Owned, RGB and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ArturSkowronski; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Minipainter.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ownedfirst paint lookup and cross-brand color matching
Ownedfirst matching: lookups and recommendations can prioritize paints you already have.
RGBaware search: approximate RGB values help with nearest-color matching.
Agentfriendly CLI: deterministic command output for AI integration (Claude + ChatGPT MCP).
POSIXish shell (Linux, macOS, WSL)
Selfhosted HTTP server** — a single Docker-friendly runtime with JSON storage and API endpoints
togglequit
imagedriven inventory fill from paint bottle photos
modelphoto analysis that recommends owned paints first
Builtin catalog data lives in data/catalog/ (Citadel and Army Painter, kept in version control)
paint_searchpaint_show
inventory_listinventory_mark_owned
inventory_mark_unownedmatch_color
PORTlisten port, defaults to 3000

How to install the Minipainter MCP server

{
  "mcpServers": {
    "minipainter": {
      "command": "npx",
      "args": ["-y", "minipainter"],
      "env": {
        "INVENTORY_SYNC_TOKEN": "your-value",
        "PORT": "your-value",
        "INVENTORY_PATH": "your-value",
        "DATABASE_URL": "your-value",
        "AUTH_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
INVENTORY_SYNC_TOKENCredential the server authenticates with.Yes
PORTConfiguration value read at startup.Optional
INVENTORY_PATHFilesystem location the server is allowed to use.Optional
DATABASE_URLEndpoint or connection string the server talks to.Yes
AUTH_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Minipainter to owned.
  • Use Minipainter to Owned.
  • Use Minipainter to RGB.

Frequently asked questions

It connects Minipainter to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (owned, Owned, RGB, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Minipainter directly.