PluginBench
MCP Server

Control AutoCAD MCP Server MCP Server

net.dmytro-prototypes/cad-control-mcp-server

Registry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Control AutoCAD MCP Server MCP server?

Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots.

How to install Control AutoCAD MCP Server

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "cad-control-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@dmytro-prototypes/cad-control-mcp-server"
      ]
    }
  }
}

Related MCP servers

Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots.

Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots.

FAFatstack logo

Fatstack

Active

Paid MCP tools behind one endpoint. Agents pay per call in USDC on Base via x402.

0
TypeScript
MIT
View repository →

Manage HepCloud (Turkish cloud) servers and managed PostgreSQL from your AI assistant. OAuth 2.1.

Build, preview, deploy and export academic surveys: blocks, flow logic, experiments, quotas, data.

Record agent tasks, get back how many finished without a human. Closed beta, nothing billed.