Cartograph MCP server

cartograph-mcp

mcp-name: io.github.benteigland11/cartograph

Tired of vibe coding the same solutions over and over? Time to stop spending money on redundant tokens and start spending it on innovative solutions.

This MCP server is for Cartograph that exposes the daily widget workflow for agents without mirroring the entire CLI. It targets the MCP 2.0 SDK contract and returns the standard ListToolsResult envelope from tools/list. On installation of the MCP the CLI will be installed automatically. Once you have it, Search, inspect, install, create, validate, check in, custom rules, and configure Cartograph defaults through a compact agent-facing surface, then fall back to the CLI for the full administrative and recovery surface.

It is highly recommended to use the plugins for the skills that go with this MCP. It will give your agent what it needs to explain a lot of the configuration and give you a very powerful workflow tool.

Why this exists

I personally have spent hours and hours working on solutions I'm proud of, only to hit a wall trying to get the same one done. The reality was prompting was never good enough, I needed a way to know my llama.cpp server client integration was going to be the same everytime I used it. I also needed to know that when I found an improvement, that improvement would stick.

If you are sick and tired of wasting money and time on redoing things you've done before, like a mouse on a wheel then get your agents to start using Cartograph.

The Cartograph CLI is the source of truth, but agents do better when the common path is small and explicit.

This MCP keeps the top-level tool surface focused on daily driving:

• finding reusable widgets
• inspecting and installing them
• managing installed widget copies
• creating new widgets
• validating and checking them back in
• adjusting the core Cartograph defaults that affect normal workflow

Everything else stays in the CLI. That keeps the MCP easier to teach, easier to test, and less likely to drift into a second full interface.

Quick start

pip install cartograph-mcp

Claude Desktop example:

{
  "mcpServers": {
    "cartograph": {
      "command": "cartograph-mcp"
    }
  }
}

The package depends on cartograph-cli and shells out to it as the source of truth for the full command surface.

Common CLI setup commands:

# Claude Code
claude mcp add cartograph --scope user -- cartograph-mcp

# Codex
codex mcp add cartograph -- cartograph-mcp

# Gemini CLI
gemini mcp add cartograph cartograph-mcp

# Cursor
cursor --add-mcp '{"name":"cartograph","command":"cartograph-mcp"}'

Claude Code expects an explicit scope flag such as --scope user.

Tool surface

The MCP intentionally exposes a small workflow-oriented surface:

Actions: search, inspect, install, rate

• registry_widget

Actions: upgrade, uninstall

• installed_widget

• widget_status
• create_widget
• validate_widget
• checkin_widget
• cartograph_config
• cartograph_rules

These are not a 1:1 mirror of the CLI. They are grouped around agent intent:

• registry-facing work
• installed-widget mutation
• project health/status
• widget authoring
• workflow configuration
• custom validation rules

Example workflow

1. Search the registry before writing logic.
2. Inspect the widget you want to reuse.
3. Install it into the project.
4. If no existing widget fits, create one.
5. Validate it with the full dry-run pipeline.
6. Check it in with a reason once it is ready.

In Cartograph terms:

Shortened. The full README is on GitHub.