← Open Source
daobataotie

CAD-MCP

CAD MCP Server.

AI EngineeringGive agent toolsProtocolsPython
Open on GitHub
Momentum
+3stars in 24 hours+0.5%
612
Stars
89
Forks
+24
This week
1
Contributors
Created 2025-03-24 · Updated 2026-10-16 · #3189 today
Top developers
daobataotie

daobataotie/CAD-MCP is ranked 3,189 with 612 stars.

Same-category comparison

daobataotie/CAD-MCP is ranked 3,189 among these 8 peers; MichaelKinsy/PiG is ranked 3,192.

Same-category comparison
NameRankMetrics
chainbase-labs/Agentkey3,177
Language:
Shell
Stars:
663
Forks:
68
LifelongLazyLearner/qu-ai-wei3,179
Language:
Shell
Stars:
660
Forks:
49
lc2panda/wps-skills3,180
Language:
TypeScript
Stars:
651
Forks:
56
redis/mcp-redis3,182
Language:
Python
Stars:
637
Forks:
120
Description:
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently.
MichaelKinsy/PiG3,192
Language:
Go
Stars:
608
Forks:
48
Description:
PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language.
8beeeaaat/touchdesigner-mcp3,200
Language:
TypeScript
Stars:
585
Forks:
62
Description:
MCP server for TouchDesigner.
puran-water/autocad-mcp3,206
Language:
Python
Stars:
571
Forks:
94
Description:
MCP server for AutoCAD LT v3.1: freehand AutoLISP execution, 8 consolidated tools, File IPC + ezdxf backends, focus-free dispatch, undo/redo, P&ID symbols, and robust IPC with ESC prefix and UTF-8 fallback. Companion agent skill: puran-water/autocad-drafting.
HRuiCcc/RuiC-card-skill3,214
Language:
JavaScript
Stars:
552
Forks:
40
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryAI Engineering
SubcategoryGive agent tools, Protocols
KeywordsAgent-ready APIs, Automation, Design, MCP
Stars612
Forks89
Contributors1
Created date2025-03-24
Updated date2026-10-16
Stars in 1 day3
Stars in 7 days24
Rank3,189
Previous rank1,523
Rank change-1,666
7-day stars rank2,487
Previous 7-day stars rank2,622
7-day stars rank change135
Total stars rank16,508
Previous total stars rank16,556
Total stars rank change48
README summary

This project combines natural language processing and CAD automation technology, enabling users to create and modify CAD drawings through simple text commands without manually operating the CAD interface. Features CAD Control Functions **Multiple CAD Software Support**: Supports mainstream CAD software including AutoCAD, GstarCAD (GCAD) and ZWCAD **Basic Drawing Functions**: Line drawing Circle drawing Arc drawing Ellipse drawing Rectangle drawing Polyline drawing Text addition Pattern filling Dimension annotation **Query Functions (the AI can see the actual drawing content)**: List all layers

List entities in model space (returns editable entity handles) Query detailed entity properties by handle (coordinates/radius/text content, etc. ) Screenshot of the CAD window for preview **Editing Functions**: erase, move, rotate, scale, copy, mirror, offset, array (linear/polar), undo/redo **Layer Management**: Create and switch layers, query layer states **Drawing Management**: New / open / close / save drawings (DWG/DXF) **Block Operations**: Create, insert, and list blocks **Command Passthrough**: Execute any CAD command via (an escape hatch for everything else) MCP

Protocol Features **Structured Output**: All tools return with an that clients can parse directly **Tool Annotations**: Query tools are marked ; destructive operations are marked for client confirmation policies **Progress Notifications**: Long-running operations (CAD startup, saving) send message notifications to the client **Dual Transport Modes**: (local, single client) and (remote / multiple clients sharing one CAD instance) **Error Semantics**: Input validation errors are returned as tool errors, enabling model self-correction Natural Language Processing Functions (legacy interface) **Command Parsing**: Parse natural

language instructions into CAD operation parameters **Color Recognition**: Extract color information from text and apply it to drawing objects **Shape Keyword Mapping**: Support recognition of various shape description words **Action Keyword Mapping**: Recognize various drawing and editing actions Demo The following is the demo video. Installation Requirements Dependencies System Requirements Windows operating system Installed CAD software (AutoCAD, GstarCAD, or ZWCAD) Python 3. 10+ Configuration The configuration file is located at and contains the following main settings: **server**: Server name, version

, and transport settings : Transport mode, (default, local single client) or (remote / multi-client) / : Listen address and port for Streamable HTTP mode (can also be overridden via / command-line arguments) **cad**: : CAD software type (AutoCAD, GCAD, GstarCAD, or ZWCAD) : CAD startup waiting time (seconds) : Command execution delay (seconds) **output**: Output file settings Usage Starting the Service Connect from an MCP Client The server uses transport by default, so the same JSON config works for any MCP client (Claude Desktop, Cursor, Windsurf

, TRAE, etc. Add it to your client's MCP server config file (e. , Cursor's ), replacing the path with your own: For Streamable HTTP mode, point the client to instead. MCP Inspector Service API The server provides the following tools (35 in total): **Basic drawing:** : Draw a line : Draw a circle : Draw an arc : Draw an ellipse : Draw a polyline : Draw a rectangle : Add text : Draw a hatch pattern : Add linear dimension **Query:** : List all layers : List entities in model space (returns

editable handles) : Query detailed entity properties by handle : Capture the CAD window to confirm drawing results **Editing:** / / / : Erase / move / rotate

Frequently asked questions

How many stars and forks are recorded?

daobataotie/CAD-MCP has 612 stars and 89 forks.

What is the repository rank?

daobataotie/CAD-MCP is ranked 3,189.

What language and category are recorded?

daobataotie/CAD-MCP has 612 stars, uses Python and belongs to AI Engineering.

Which repository is closest in rank?

daobataotie/CAD-MCP is compared with MichaelKinsy/PiG, ranked 3,192 with 608 stars.

Nearby in the ranking
Similar items