Skip to main content
Glama
AutoCAD MCP

AutoCAD MCP

run_command

Sends direct AutoCAD command-line strings via COM for operations not covered by dedicated tools; use underscore-prefixed English command and option names.

Instructions

ПРЯМАЯ КОМАНДА AutoCAD (только COM): строка как в командной строке, напр. '.CHAMFER' или '.FILLET _R 50'. Пробел/Enter в конце добавляется сам. Пишите английские имена команд и опций с префиксом _ (они работают в AutoCAD на любом языке). Выполняется без проверок, используйте, когда нет подходящего инструмента.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "command": "<command>"
    },
    "name": "run_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose key behavior: execution happens 'without checks' (no validation or confirmation), a trailing space/Enter is appended automatically, and the transport is COM-only. It does not spell out failure behavior or that arbitrary commands can modify or destroy drawing content, leaving a modest gap for an unguarded execution tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the tool's identity and the 'only COM' constraint, then gives examples, then formatting rules, then the usage rule. Every sentence carries information; only the language-prefix explanation is slightly wordier than needed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the one required parameter is fully characterized. For a no-check command passthrough, the remaining gap is error/failure reporting and any restriction on interactive commands, which an agent would benefit from knowing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single 'command' parameter is undocumented in the schema, so the description must compensate — and it does, specifying the string format, the required '_' prefix on English command and option names, and that a trailing space/Enter is added automatically. It omits whether multiple commands can be chained or how to pass coordinate input, which keeps it below a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: it sends a raw AutoCAD command-line string over COM, with concrete examples ('_.CHAMFER', '_.FILLET _R 50'). It also distinguishes itself from the drawing/dimension siblings by declaring itself the escape hatch for cases with no suitable dedicated tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use it 'when there is no suitable tool', which is a real fallback rule and steers the agent away from it for routine drawing tasks. It lacks a stated when-not beyond that (e.g. no warning about interactive commands that block), so it stops short of the top band.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.