Files
cadcraft/docs/mcp.md
T
8abc0909f3 MCP: render one area of the drawing, and read its texts (find_text) (#757)
A render of a large drawing (a set of sheets in model space) fits every
sheet in one image, too small to read. `render` takes `window`
[[x0,y0],[x1,y1]]: just that area, 1600 px wide with the window's shape
unless sized (the app's and the headless `ui.render` both; the display list
is built for that view only). `View::of_window` sizes it.

`find_text` (engine command `texts`, read-only) returns the readable text of
TEXT, MTEXT (formatting removed), block attributes and multileaders with
insertion point, height, rotation, style, layer and handle, filtered by
content, layer and a window. FIND selects and can replace; this only
reports, so an agent can find room names, sheet numbers and titles without
reading all the geometry.

On a 39,600-object permit set: 5,861 texts in 0.02 s; one 90 x 59.4 sheet
rendered at 2400 x 1584 in 0.5 s.

Co-authored-by: Claude Opus 5.5 <[email protected]>
Co-authored-by: Brandon Thomas <[email protected]>
2026-10-13 05:34:34 -04:00

3.9 KiB

CADCraft and AI agents (MCP)

CADCraft speaks the Model Context Protocol over stdio.

Start it

# Headless: an in-process drawing session, no window.
cadcraft-cli mcp

# Bridged to the running app (watch the agent draw):
cadcraft --control 7979 &
cadcraft-cli mcp --connect 127.0.0.1:7979

An MCP client usually starts its servers when it starts, often before the app is open. With --lazy the bridge starts anyway and reaches the app at the first tool call; until the app answers, each call fails with a message saying how to open it. --launch also opens CADCraft (macOS) with that control port at a call that finds nothing, and waits for it:

{ "mcpServers": { "cadcraft": { "command": "cadcraft-cli", "args": ["mcp", "--connect", "127.0.0.1:7979", "--launch"] } } }

--connect needs the app's HOST:PORT. Without one (or with an unknown argument) cadcraft-cli mcp exits with an error instead of falling back to a headless session, so a client meant for the app never edits a separate drawing by mistake. If the app can't be reached, startup fails too.

Example client configuration (Claude Code / Claude Desktop):

{ "mcpServers": { "cadcraft": { "command": "cadcraft-cli", "args": ["mcp"] } } }

Tools

Tool What it does
command_line {text} Type at the command line exactly like a person: line 0,0 @10,0 @0,5 c, circle 5,2 1, offset 0.5, zoom e. Spaces act as Enter; empty text is Enter. Returns the new prompt, keywords and output.
script {text} A multi-line script (like .scr files).
execute {command, params} Any command with JSON parameters, never a dialog. list_commands shows ids and parameter docs.
list_commands {filter?} The command catalog; filter matches part of a command's id, label or an alias.
inspect_drawing {entities?, limit?} Counts, extents, layers, styles, blocks, layouts, selection, undo history and entities.
query_entities {type?, layer?, window?, crossing?, limit?, offset?} Filtered entities with handles and geometry. window [[x0,y0],[x1,y1]] finds objects whose geometry is inside it or crosses it (crossing: false: entirely inside). count is every match, returned the page (offset, limit, default 500).
render {width?, height?, fit?, window?} A PNG image of the drawing, or of just the area window [[x0,y0],[x1,y1]] (one sheet or room of a large drawing; 1600 px wide with the window's shape unless sized).
find_text {contains?, layer?, window?, limit?, offset?} The readable texts — TEXT, MTEXT without formatting codes, block attributes, multileaders — with text, insertion point, height, rotation, style, layer and handle; filtered by content (any case), layer and a window around the insertion points. Read-only (the texts command).
new_drawing {metric?}, open {path}, save {path?}, cancel Files and Escape. save to a .svg, .png or .pdf path exports: the drawing keeps its name and unsaved changes.
screenshot, ui_inspect, ui_click {x, y} Only when connected to the app.

Resources: cadcraft://drawing (inspect JSON) and cadcraft://commands (catalog).

Arguments are checked against each tool's input schema. An unknown tool, arguments that aren't an object, a missing required argument or one of the wrong type is a JSON-RPC error -32602 (invalid params), so command_line {} never presses Enter by accident. A tool that runs and fails (a bad point, an unknown command) returns a result with isError: true and the message.

A typical session

  1. command_line {"text": "rectang 0,0 100,60"}
  2. execute {"command": "circle", "params": {"center": [10, 10], "radius": 4}}
  3. command_line {"text": "dimlinear 0,0 100,0 50,-8"}
  4. inspect_drawing {} — verify counts and geometry.
  5. render {} — look at it.

The end-to-end test in crates/mcp/src/tests.rs runs a session like this and checks the result only through MCP.