Execute build123d Python code in the persistent session. Use show(shape, name) to register named objects (name defaults to 'shape'); show() immediately prints volume and face count confirming the shape is non-empty. After any boolean operation (-, +, &) call measure(topology) or measure(volume) to confirm it succeeded before calling render_view.

Render model. format: 'png' (raster, default), 'svg' (HLR line drawing — works without a display, no shading but precise edges), or 'both' (returns the PNG and SVG together — useful when you want shaded depth cues plus crisp edge geometry). If the raster path fails (typically headless host with no display backend) and format='png', the server falls back to SVG automatically. Renders confirm appearance, not geometry — verify boolean operations with measure() before rendering. direction: top, front, side, iso. objects: comma-separated names or name:color pairs e.g. 'u_frame:blue,roller:red' (default: all, auto-coloured). quality: standard, high. clip_plane: x, y, z to slice; clip_at: absolute world coordinate along that axis (default: each mesh's midpoint). azimuth/elevation: camera rotation in degrees applied after the direction preset. save_to: optional file path; for format='both' the PNG and SVG are written as <save_to>.png and <save_to>.svg.

Query geometry of a shape. Prefer measure over render_view when verifying geometry — numbers are unambiguous. query: bounding_box, volume, area, min_wall_thickness, clearance, topology, summary. summary returns bbox + volume + area + topology + center in one call — use it to orient quickly. topology (face/edge/vertex counts) is the fastest way to confirm a boolean operation succeeded: a cut that failed leaves the counts unchanged. object_name/object_name2: named objects from show() (clearance requires both).

Export model. format: step, stl, or comma-separated list e.g. 'step,stl'. object_name: named object from show(), '*' to export all named shapes as a combined assembly (default: current shape).

Check whether two named objects (from show()) intersect. Returns interferes (bool), volume (mm³ of overlap), and bounds of the interference region.

Search the part library. query: keywords matched against name, description, tags, category (empty returns all). Returns name, category, description, tags, and full parameter specs including types, defaults, and descriptions.

Load a named part from the library into the session. name: part name from search_library. params: optional JSON object of parameter overrides e.g. '{"od": 8.0, "length": 20.0}' — unspecified params use their defaults. The part is registered as a named object and becomes current_shape.

List all named shapes registered via show(), each with volume (mm³), face, edge, and vertex counts. Call this to audit session state without guessing what show() has been called on.

Save a named checkpoint of the current geometric state (current_shape and the show() object registry). The Python variable namespace is NOT saved — only geometry. Call this before risky experiments so you can restore known-good geometry without re-running all prior execute() calls.

Restore geometric state from a previously saved snapshot (current_shape and the show() registry). The Python variable namespace is NOT restored — execute() calls made after the snapshot are still in scope, but current_shape and all show() objects revert to what they were at snapshot time. Raises an error if the snapshot name does not exist.

Compare two snapshots by geometry metrics (volume, topology, bounding box). snapshot_b defaults to current session state if omitted. format: 'text' (default, human-readable) or 'json' (structured, for programmatic consumption).

Return a structured JSON snapshot of the current session: current_shape metrics, all named objects with geometry stats, snapshot names, and a variables summary of the Python namespace (type + volume for shapes, type + length for collections, type + value for scalars). Use this to orient after a reset, restore, or multi-step build to confirm what geometry and variables are active.

Verify that render and export dependencies are working. Tests PNG render (VTK), SVG render (build123d HLR), STEP export, and STL export with a trivial shape. Returns JSON with ok/error per capability. Run at session start if you suspect a missing dependency.

Clear the current session back to empty state, including all snapshots.

Check build123d code for syntax errors, blocked imports/calls, and common omissions before executing. Returns {syntax, blocked, warnings, ok}. blocked items prevent execution; warnings are advisory (e.g. no build123d import in this snippet, no result/show() call). Use this before a long generated script to catch obvious problems without burning a session execute().

Compare two named shapes (from show()) by geometry metrics: volume delta, bbox delta, topology delta (faces/edges/vertices), and center offset. Useful when you have an intended design and a reference/test shape and want to verify they match — or to quantify how a modification changed the geometry.

Given an error message from execute(), return targeted fix suggestions for common build123d mistakes: wrong Location syntax, missing .part, CadQuery idioms, blocked imports, degenerate boolean results, fillet edge selection, and more. Pass the full error string from execute() or last_error().

Return details of the last failed execute() call: exception type, message, and (for runtime and syntax errors) line number and a 5-line excerpt around the failing line. Security errors include a message but no line/excerpt. Returns {"error": null} if the last execute() succeeded or no execute() has failed yet. Call this immediately after an execute() error to get the exact failing line — much faster than re-reading the submitted code.

Return the build123d-mcp server version.

Return guidance on how to use these tools effectively. Call this at the start of a session or whenever unsure which tool to reach for.