Skip to main content
Glama
Sign In
CAD MCP Server

CAD MCP Server

by 652036
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

autocad_send_command

Submit a raw command to the live AutoCAD document via COM, rejecting busy or inactive documents. Use it to automate drawing edits when direct command execution is required.

Instructions

Submit a raw command to the live AutoCAD document. Rejects a busy document or a bound document that is no longer active. Example: _.ZOOM _E. waitForIdle defaults to false; true polls for idle for timeoutMs (1000–30000 ms) after the COM SendCommand call returns. A separate 45-second bridge timeout bounds blocking COM calls. Result state is submitted, idle_observed or timeout; none proves semantic command success. timeout is an MCP error with result data. Query intended results afterward. Submission is not retried; after an error or timeout do not resend before inspecting the drawing.

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": "autocad_send_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes
timeoutMsNo
waitForIdleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries full burden and does so richly: rejection conditions, waitForIdle polling semantics, a separate 45-second bridge timeout, possible result states, the caveat that no state proves semantic success, MCP-error-on-timeout behavior, and a no-retry policy. This is unusually thorough failure-mode disclosure.

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-loaded with the core purpose and example, then builds out constraints, timing, and failure semantics. Dense but each sentence conveys distinct operational information; slightly packed but nothing is clearly wasted.

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?

For a complex, annotation-free tool with no output schema, the description covers failure modes, timing, and result-state semantics thoroughly. Minor gap: no guidance on which structured siblings supersede it or formatting rules for the command string.

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%, so the description must compensate. It explains waitForIdle's default and polling window, the timeoutMs range (1000-30000) and its relationship to idle polling, and gives a command syntax example. The command parameter itself could use more formatting guidance, but the two behavioral params are well covered.

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 ("Submit a raw command to the live AutoCAD document") and includes a concrete example (`_.ZOOM _E`). It is clearly distinguishable from the many structured autocad_* and geometry siblings as the raw escape-hatch 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?

Gives clear operating context: rejects busy/inactive documents, explains when waitForIdle should be toggled, and instructs to query intended results afterward and not to resend after error/timeout. It does not, however, explicitly state when to prefer this raw tool over the structured siblings.

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

Deploy Server

Other Tools