tldraw
Draw and visually collaborate with your agents on tldraw's canvas.
使うべきか
品質と安全性
検出事項(2)
- LOW_exec_callback 内
- LOW_get_canvas_state 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"tldraw": {
"url": "https://tldraw-mcp-app.tldraw.workers.dev/mcp"
}
}
}リモートエンドポイント
https://tldraw-mcp-app.tldraw.workers.dev/mcpstreamable-httphttps://tldraw-mcp-app.tldraw.workers.dev/ssesseできること
ツール一覧
ツール(6)
🟢search(code)
Search the tldraw Editor API spec by writing JavaScript that receives a `spec` object and returns a result. The spec contains: spec.members (all Editor methods/properties with name, kind, signature, description, category), spec.categories (category names), spec.types.shapes (focused shape type definitions with props), spec.types.shapeTypes (list of all shape type strings), spec.helpers (exec helper functions with descriptions, params, examples). Examples: - Find shape methods: return spec.members.filter(m => m.category === "shapes").map(m => ({ name: m.name, signature: m.signature })) - Get arrow shape props: return spec.types.shapes.find(s => s.shapeType === "arrow") - List all categories: return spec.categories - Find a helper: return spec.helpers.find(h => h.name === "createArrowBetweenShapes")
入力スキーマ
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "JavaScript code that receives `spec` and returns a result. Must use `return` to produce output."
}
},
"required": [
"code"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡exec(code, canvasId)
Execute JavaScript code on a tldraw canvas. The code runs in the widget with access to the live `editor` instance, helper functions, and normal js. Use the `search` tool first to discover available Editor methods and shape types. Each canvas has a unique `canvasId`. Omit `canvasId` to create a new blank canvas. To edit an existing canvas, pass the `canvasId` that was returned by a previous exec call. Shapes and text grow depending on the amount of text they have. Use clever scripting to ensure there are no unintended overlaps. Examples: - Create a rectangle: editor.createShape({ _type: 'rectangle', shapeId: 'box1', x: 200, y: 120, w: 320, h: 180, text: 'Hello' }) - Connect shapes with an arrow: editor.createShape({ _type: 'arrow', shapeId: 'a1', fromId: 'box1', toId: 'box2', x1: 0, y1: 0, x2: 100, y2: 0 }) - Select and zoom: editor.select('box1'); editor.zoomToSelection() - Read shapes: return editor.getCurrentPageShapes() - Distribute evenly: editor.distributeShapes(editor.getSelectedShapeIds(), 'horizontal') - Box around shapes: boxShapes(['box1', 'box2'], { text: 'Group label', color: 'blue' }) - Stack shapes dynamically: editor.createShape({ _type: 'rectangle', shapeId: 'a', x: 0, y: 0, w: 300, h: 200, text: 'First box\nwith wrapping text' }); const bounds = editor.getShapePageBounds('a'); editor.createShape({ _type: 'rectangle', shapeId: 'b', x: 0, y: bounds.maxY + 20, w: 300, h: 200, text: 'Below first' })
入力スキーマ
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "JavaScript code to execute. Has access to `editor` (tldraw Editor instance) and helper functions."
},
"canvasId": {
"description": "Canvas ID to edit. Omit to create a new blank canvas. Pass a canvasId from a previous exec result to continue editing that canvas.",
"type": "string"
}
},
"required": [
"code"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪_exec_callback(channel, execKey, result, error)
App-only: widget calls this to resolve a pending exec request.
入力スキーマ
{
"type": "object",
"properties": {
"channel": {
"type": "string"
},
"execKey": {
"type": "string"
},
"result": {
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"result": {},
"error": {
"type": "string"
},
"canvasId": {
"type": "string"
}
},
"required": [
"success"
]
},
"error": {
"type": "string"
}
},
"required": [
"channel"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢_get_canvas_state(canvasId)
App-only: get the latest checkpoint for a canvas by its canvasId.
入力スキーマ
{
"type": "object",
"properties": {
"canvasId": {
"type": "string",
"minLength": 1
}
},
"required": [
"canvasId"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢read_checkpoint(checkpointId)
App-only: read shapes from a checkpoint by ID.
入力スキーマ
{
"type": "object",
"properties": {
"checkpointId": {
"type": "string",
"minLength": 1
}
},
"required": [
"checkpointId"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡save_checkpoint(checkpointId, shapesJson, assetsJson, bindingsJson, canvasId)
App-only: save shapes to a checkpoint (from user edits). shapesJson and assetsJson must be JSON array strings.
入力スキーマ
{
"type": "object",
"properties": {
"checkpointId": {
"type": "string",
"minLength": 1
},
"shapesJson": {
"type": "string"
},
"assetsJson": {
"type": "string"
},
"bindingsJson": {
"type": "string"
},
"canvasId": {
"type": "string"
}
},
"required": [
"checkpointId",
"shapesJson"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス