- Add packages/mcp/src/stdio.ts — proper stdio MCP server that
connects to the running app via WebSocket
- openpencil-mcp bin now points to stdio entry (was HTTP)
- openpencil-mcp-http bin added for the HTTP server
- Extract registerTools() from server.ts to share between transports
- Move index.ts banner output to stderr (prevents stdout corruption)
- Update Tauri shell spawn to use openpencil-mcp-http
- Update all docs (EN + 6 translations): correct binary names, source
paths, port number
Fixes#194
- Add save_file MCP tool that proxies to the browser app via RPC
- Add save_file RPC handler in the automation server
- Rebuild dist/ to fix stale @open-pencil/core/* self-referencing imports
from before the domain module restructuring
Fixes#184Closes#185 (save_file added; open_file requires File System Access API
which is browser-interactive; new_document needs a store reset method)
Remove headless SceneGraph mode — the MCP server now always proxies
tool calls to the browser via WebSocket. One server, one architecture:
HTTP :7600 — /health, /rpc (CLI), /mcp (MCP Streamable HTTP)
WS :7601 — browser connects, executes tool calls against live editor
- Delete http.ts (merged into server.ts)
- Delete headless SceneGraph, open_file, save_file, new_document
- Delete canvaskit-wasm dependency (no headless rendering)
- Add ws dependency for WebSocket server
- Rewrite tests with mock browser over real HTTP+WebSocket
- Simplify bridge.ts to 6 lines (just imports and starts the server)
- Replace ssrLoadModule hacks with direct imports from @open-pencil/core
- Replace isBunRuntime() hack with @hono/node-server (works everywhere)
- Remove ViteServer type parameter from startAutomationBridge
- Upgrade @open-pencil/mcp zod dependency from v3 to v4
- Add @open-pencil/mcp as root devDependency for bridge imports
ACP agents now get an MCP server at http://127.0.0.1:7600/mcp that
proxies tool calls through the automation WebSocket to the browser,
where they execute against the live editor store. No separate
subprocess, no stale npm package — tools operate on the open canvas.
- Add /mcp endpoint to automation bridge (Streamable HTTP transport)
- Each MCP tool call → sendToBrowser({command:'tool'}) → browser executes
- Strip mcp__open-pencil__ prefix from tool names in chat UI
- Export paramToZod from MCP package for bridge reuse
Pass openpencil-mcp as a stdio MCP server to the ACP session so
agents get all design tools (create shapes, render JSX, export
images, etc.) instead of just plain conversation.
- Add makeFigma option to createServer for external FigmaAPI injection
- Skip file lifecycle tools (open/save/new) when using external FigmaAPI
- Pass MCP server config in ACP newSession mcpServers
- Add bun to Tauri shell scope for MCP server subprocess
* feat(mcp): add export_image_file tool — saves PNG/JPG/WEBP to disk
The existing export_image tool returns base64 inline, which MCP clients
display in chat but don't save to disk. This new tool writes the image
directly to a file path, making exports usable for documentation,
mockup reviews, and CI pipelines.
Parameters:
- path: absolute file path to save (required)
- ids: node IDs to export (optional, defaults to all top-level nodes)
- format: PNG | JPG | WEBP (default: PNG)
- scale: 0.1–4 (default: 2)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(mcp): add export_image_file tool and fix headless PNG rendering
**New tool: `export_image_file`**
Saves rendered PNG/JPG/WEBP images directly to a file path on disk.
The existing `export_image` returns base64 inline — useful for chat
but doesn't produce files. AI agents and CI pipelines need actual files.
Path validation runs before the expensive render call. The tool
respects `fileRoot` restrictions.
**Fix: headless PNG rendering now matches the editor**
1. `computeAllLayouts()` called after `render` creates nodes via JSX.
2. Bundled Inter font loaded from disk — tries `../fonts/` (installed
package) then `../../public/` (project root). The web-based
`fetch('/Inter-Regular.ttf')` fails in Node.js.
3. Text measurement uses `renderer.measureTextNode()` — the same
ParagraphBuilder the renderer uses to draw text. Measurement and
rendering use the same SkiaRenderer instance, same fontProvider,
same font shaping. Zero hacks.
Export pipeline:
ensureInterFont() → SkiaRenderer + loadFonts() →
setTextMeasurer(renderer.measureTextNode) →
computeAllLayouts() → renderNodesToImage()
**Tests added** (6 new tests in mcp-server.test.ts):
- export_image_file produces valid PNG after render
- export_image_file without ids exports all page children
- export_image_file without document returns error
- export_image_file with out-of-root path returns error
- JPG and WEBP formats produce non-empty output
- export_image_file is listed in tools
* Remove .cue directory and revert .gitignore changes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Move computeAllLayouts into renderTree, reuse exportImage in MCP
computeAllLayouts was in the render tool but renderJSX has multiple
callers (render, replace_node, automation server). Moving it into
renderTree ensures layout is always computed after JSX rendering.
export_image_file in MCP server was duplicating export_image logic.
Now delegates to exportImage.execute and just handles the file write.
---------
Co-authored-by: Michael Magsuci <mcdmag@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Danila Poyarkov <dev@dannote.net>
CLI headless only loaded one 'Regular' style per font family and never
initialized the CanvasKit font provider, so all text rendered with
fallback glyphs or wrong weights.
Extract headlessRenderNodes/headlessRenderThumbnail into core's
headless-render.ts — handles CanvasKit init, renderer creation, font
provider setup, per-weight font loading via collectFontKeys, and
rendering in one call. Both CLI and MCP server now use this shared
module instead of duplicating the setup.
When corners have different radii, node.cornerRadius returns
Symbol('mixed') which can't be serialized to JSON, breaking AI SDK
tool results. Return individual radius values instead.
Also remove unused initFontService import from MCP server.
Co-authored-by: Anton Soldatov <eddclyde@yandex.ru>
Closes#109
Guard `window.queryLocalFonts` for non-browser runtimes (Bun/Node),
load fonts in MCP `export_image` handler before rasterization, and
ensure `stackChildAlignSelf` serialization block is properly scoped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace calc.ts (150 lines) with expr-eval library
- Replace rgbLuminance with culori wcagLuminance
- Use @iconify/utils iconToSVG for viewBox normalization in iconify.ts
- Extract describe-shared.ts: findAncestorBackground, looksLikeButton, CONTAINER_TYPES
- Extract icon-render.ts: shared createIconFromPaths for create.ts and renderer.ts
- Inline codegen prompt as TS constant, remove runtime fs.readFile from MCP server
- Fix blur effect color alpha (a:1 → a:0)
- Encapsulate module-level mutable state in src/ai/tools.ts into RunState class
- Add network check to iconify tests (skip gracefully offline)
- Remove Caddyfile.dev and components.d.ts from tracking, add to .gitignore
- Remove docs/mcp-codegen-plan.md (internal planning doc, not for repo)
- Remove lol.fig test fixture left in repo root
- Fix inline type imports in codegen.ts — use top-level SceneGraph import
- Move get_codegen_prompt out of core/ALL_TOOLS into MCP server only
(core must be browser-safe, node:fs is not available in browser)
- Remove skill from packages/mcp/skills/ — content saved to #97
- Slim down codegen.md overlap note (canonical reference stays there)
Closes review comments. Skill npm publishing tracked in #97.
- Add index signature to NodeChange for Kiwi codec fields
- Add blobs field to FigmaMessage
- Use 'in' type guards instead of Record casts in ai-adapter
- Use Object.fromEntries for Partial<SceneNode> property copying
- Use satisfies instead of as for handle position map
- Type node() to accept { children?: unknown; [key: string]: unknown }
- Remove ext() helper in kiwi-convert (direct property access)
37 occurrences → 1 (Kiwi codec boundary only).
13 tests using InMemoryTransport from @modelcontextprotocol/sdk:
- Tool registration (all 76 tools listed with descriptions)
- new_document, open_file, save_file lifecycle
- Tool execution through MCP protocol (create, fill, delete, query)
- Error paths: no document loaded, nonexistent node, invalid file path
- Full workflow: new → create → nest → query → delete
Fix @open-pencil/core dep in MCP package: workspace:* for local dev
(pnpm publish resolves this to the actual version at publish time).
29 tools: open_file, save_file, new_document + all 26 from @open-pencil/core.
Stdio for MCP clients (Claude Code, Cursor), HTTP (Hono + Streamable HTTP
with sessions) for scripts, browser extensions, CI.
Runs on both Bun and Node.js (via tsx).
