mirror of
https://github.com/storytold/cadcraft.git
synced 2026-10-24 19:06:56 -06:00
Valentin KleinandClaude Opus 5.5
bcbbc5e8a4
* cadcraft-cli mcp: --connect without HOST:PORT is an error, not a headless session (#103) `mcp --connect` with no address (or an empty or flag-like one) fell through to the headless backend, so a client meant for the app got successful edits in a separate drawing. The mcp arguments now go through parse_mcp_args: --connect must be followed by a non-empty value that doesn't start with `-`, unknown arguments and a repeated --connect are rejected, and every error exits non-zero before any MCP request is served. Plain `mcp` is still headless; a real address still connects, and an unreachable one still fails. - Unit tests for the parser; integration tests (tests/mcp_connect.rs) run the binary: missing/empty/flag-like address, headless control, loopback endpoint routing, closed port. - docs/mcp.md says what happens without an address. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Move tests away from other PRs' hunks to avoid merge conflicts Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2.2 KiB
2.2 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
--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. |
inspect_drawing {entities?, limit?} |
Counts, extents, layers, styles, blocks, layouts, selection, undo history and entities. |
query_entities {type?, layer?, window?} |
Filtered entities with handles and geometry. |
render {width?, height?, fit?} |
A PNG image of the drawing. |
new_drawing {metric?}, open {path}, save {path?}, cancel |
Files and Escape. |
screenshot, ui_inspect, ui_click {x, y} |
Only when connected to the app. |
Resources: cadcraft://drawing (inspect JSON) and cadcraft://commands (catalog).
A typical session
command_line {"text": "rectang 0,0 100,60"}execute {"command": "circle", "params": {"center": [10, 10], "radius": 4}}command_line {"text": "dimlinear 0,0 100,0 50,-8"}inspect_drawing {}— verify counts and geometry.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.