io.github.YonGs-AI/leor-ai-booth-design-agent

Official23 tools

LEOR AI展台设计 Agent

AI booth design, image editing, presentation assets, and authorized LEOR project storage.

Design trade show booths with image editing and presentation asset creation.

Captured live from the server via tools/list.

connect_leor_account

Connect or check the local LEOR account connection. If LEOR is already connected, this returns connected=true and no authorizationUrl; do not treat that as failure. If authorization is missing or forceReconnect=true, it returns a fresh authorizationUrl. Do not inspect local .env, MCP config, source files, token values, or backend code.

Parameters (2)

statestring
Optional opaque state for the authorization flow. Usually leave empty.
forceReconnectboolean
Set true only after a protected LEOR tool returned authRequired=true or the user explicitly wants to reconnect. Leave false for status checks.

get_leor_agent_status

Free tool. Check LEOR Agent Gateway version, playbook version, and latest update notice. Use once when a session starts, after reconnecting LEOR, or when behavior seems stale. The gateway suppresses repeated reminders for the same noticeId, so do not manually repeat the same update notice.

Parameters (3)

seenNoticeIdstring
Optional noticeId already shown by this agent. If it matches the latest notice, LEOR suppresses the reminder.
currentPlaybookVersionstring
Optional LEOR playbook version currently known by the agent. If it matches the latest version, LEOR suppresses the reminder.
forceShowboolean
Set true only for diagnostics or when the user asks what changed.

get_leor_account_status

Free read-only tool. Check the currently authorized LEOR account status and credit balance. Use when the user asks how many credits are left, whether their LEOR account is connected, or whether they have enough credits before generation. It does not spend credits and does not expose tokens or private credentials.

No parameters.

prepare_leor_generation

Free preflight checker for LEOR credit-consuming generation tools. Use when the user wants AI image generation but the brief may be incomplete or ambiguous. It never spends credits; it returns readyToGenerate, missingFields, questionsToAsk, recommendedQuestions, reminders, and which paid tool can be called. For first-round booth generation, do not rely on defaults: collect the LEOR main left-sidebar brief, ask logo/reference decisions, summarize, and wait for explicit user confirmation before spending credits.

Parameters (40)

intendedToolstring
Paid LEOR tool name to check, for example generate_booth_directions, evolve_booth_image, generate_everything_to_booth, generate_view_angle, generate_storyboard, generate_material_board, generate_trend_poster, generate_minimal_poster, or generate_glass_poster.
userIntentstring
Short summary of what the user asked for.
promptstring
Current user-facing brief or instruction.
widthnumber
Booth width in meters when known.
depthnumber
Booth depth in meters when known.
heightnumber
Booth height in meters when known.
openingstring
Opening label or alias when known.
openingLayoutstring
Wall/opening layout in user language. Must say which of front/back/left/right are walls and which are openings. LEOR uses width as front length and depth as front-to-back.
sidesDescriptionstring
Optional side layout description. Same meaning as openingLayout.
openingLayoutConfirmedboolean
True only after the user confirmed which of front/back/left/right are walls/openings.
clientNamestring
Brand name or exhibiting company name. Required for first-round booth generation.
brandNamestring
Alias of clientName: brand name.
companyNamestring
Alias of clientName: exhibiting company name.
industrystring
展示产品 from the LEOR left sidebar, or product category/industry context. Do not use this as a substitute for the brand/company name.
targetIndustrystring
Target industry or product category for everything-to-booth.
targetUsestring
Target business use, for example proposal, product display, launch, or client meeting.
stylestring
Design style or business goal.
colorsstring
Preferred colors or brand colors.
boothShapestring
展位造型描述 from the LEOR left sidebar: facade, canopy, silhouette, spatial structure, or visual form.
additionalNotesstring
材质 & 细节补充 from the LEOR left sidebar: materials, functional zones, product display, meeting area, storage, screen, reception, and other details.
renderModelstring
Public LEOR Chinese render model name: 快速渲染模型, 专业渲染模型, or 全能渲染模型.
resolutionstring
1K, 2K, or 4K.
aspectRatiostring
Image aspect ratio, for example 16:9.
logoUrlstring
Optional brand logo image URL.
logoImageBase64string
Optional brand logo image data URL from a local image attached in the current agent conversation. JPG/PNG/WEBP only, max 25MB.
logoBase64string
Alias of logoImageBase64.
logoAskedboolean
True only after you explicitly asked whether the user has a logo.
noLogoConfirmedboolean
True only when the user explicitly says they do not have a logo or will not provide it now.
sourceImageUrlstring
Image source URL. For everything-to-booth prefer an arbitrary non-booth visual source; for other node tools use the selected booth image.
referenceImageBase64string
Optional reference image data URL from a local image attached in the current agent conversation. JPG/PNG/WEBP only, max 25MB.
sourceImageBase64string
Alias of referenceImageBase64.
referenceBase64string
Alias of referenceImageBase64.
referenceImageAskedboolean
True only after you explicitly asked whether the user has a reference image.
noReferenceConfirmedboolean
True only when the user explicitly says they do not have a reference image or will not provide it now.
exhibitItemIdstring
Optional LEOR canvas item id.
galleryItemIdstring
Optional LEOR inspiration gallery item id.
briefConfirmedboolean
True only after you summarized the collected brief and the user explicitly confirmed generation.
countinteger
Agent/MCP generation count. Must be 1. Multi-image generation is not enabled for Agent/MCP.
multiImageConfirmedboolean
Deprecated compatibility field. It does not enable multi-image generation in Agent/MCP.
countConfirmedboolean
Deprecated compatibility field. It does not enable multi-image generation in Agent/MCP.

search_inspiration_gallery

Search public approved LEOR inspiration gallery images. Use before generation when the user is vague, asks for references/cases, says 找/搜/看看/灵感广场/案例/参考图, or wants to use an existing LEOR gallery image as visual direction. A follow-up color such as 橙色方案 after a search request still means refine the gallery search; do not switch to generation. Use query for free-text words such as 建材展, 瓷砖, 橙色, or 色彩鲜艳; use industry only for exact LEOR category labels. If one search is empty, try related words before telling the user no close reference was found.

Parameters (9)

querystring
Free-text keyword such as industry, brand category, color, style, or booth feature. Prefer this for informal words like 建材展, 瓷砖, 橙色, or 色彩鲜艳.
industrystring
Exact LEOR gallery industry category filter. For informal words, prefer query; the gateway normalizes common categories.
stylestring
LEOR gallery style filter.
openingstring
Opening filter, for example 三面开口 (半岛型).
widthnumber
Optional booth width in meters.
depthnumber
Optional booth depth in meters.
pageinteger
Page number, starts at 1.
limitinteger
Result count, max should stay small for agent display.
sortstring
popular or latest.

get_inspiration_item

Get one LEOR inspiration gallery item with safe preview metadata after the user selects a reference. Search results return galleryItemId; pass that value here as galleryItemId or itemId. Use previewUrl directly for conversation display when the host supports image URLs; it is a watermarked inline preview, not the raw original. Use downloadUrl only when the host cannot display image URLs or the user explicitly asks for a local file; downloadUrl is also watermarked. Use galleryItemId for generation instead of downloading or exposing raw gallery image URLs.

Parameters (2)

galleryItemIdstring
Gallery item id returned by search_inspiration_gallery. Preferred.
itemIdstring
Alias of galleryItemId for compatibility.

generate_booth_directions

Credit-consuming: generate exactly 1 booth design image from a user brief in Agent/MCP. Use only when the user clearly wants a new generated booth image, not when they asked to find/search/browse inspiration references. Do not call this for color-only or style-only phrases such as 橙色方案. New booth design corresponds to the real LEOR website left sidebar: 客户与品牌(clientName/logo/referenceImage/industry), 空间与布局(width/depth/height/openingLayout), 设计方向(style/colors/boothShape/additionalNotes), 输出设置(resolution/aspectRatio/renderModel/count/grid). Before the first paid booth generation, give the user one copyable checklist split into Required and Optional-but-ask fields. Required: brand/company name, display product, width/depth/height, front/back/left/right wall-opening layout, visual style, colors, booth shape, materials/functions/details, render model, resolution, aspect ratio. Optional-but-ask: logo and reference image; assets are optional but the yes/no decision is required. If the user attached local images in the agent conversation, pass them with logoImageBase64/referenceImageBase64. These are transport fields only: LEOR stores the images in the authorized user project assets and uses generated asset URLs internally. Do not tell the user LEOR only accepts image URLs, and do not ask the user to convert files to base64. Agent/MCP never generates multiple images in one call. If the user asks for multiple directions, explain that LEOR will generate them one by one, each charged separately, and ask whether to start the first image. Then summarize the brief and wait for explicit user confirmation. If required brief fields are missing the tool returns needsMoreBrief and will not spend credits. LEOR backend handles prompt assembly and asset storage without exposing prompts.

Parameters (39)

promptstringrequired
Concise user-facing booth design brief assembled from the conversation. Credit-consuming: do not use for gallery/reference search intent or color-only phrases. Do not include hidden prompts or technical implementation terms.
widthnumber
Booth width in meters. If unknown, default to 6 for first exploration.
depthnumber
Booth depth in meters. If unknown, default to 6 for first exploration.
heightnumber
Booth height in meters. If unknown, default to 4 for small/medium booths.
openingstring
Opening alias or LEOR opening label.
openingLayoutstring
Wall/opening layout in user language. Must say which of front/back/left/right are walls and which are openings. LEOR uses width as front length and depth as front-to-back.
sidesDescriptionstring
Optional side layout description. Same meaning as openingLayout.
openingLayoutConfirmedboolean
True only after the user confirmed which of front/back/left/right are walls/openings.
clientNamestring
Brand name or exhibiting company name. Required for first-round booth generation.
brandNamestring
Alias of clientName: brand name.
companyNamestring
Alias of clientName: exhibiting company name.
industrystring
展示产品 from the LEOR left sidebar, or product category/industry context. Do not use this as a substitute for the brand/company name.
stylestring
Visual style such as 现代简洁, 科技感 / 未来感, 高端奢华, 环保木质.
colorsstring
Preferred colors or brand colors. If unknown, use a neutral commercial palette with one accent color.
boothShapestring
展位造型描述 from the LEOR left sidebar: facade, canopy, silhouette, spatial structure, or visual form.
additionalNotesstring
材质 & 细节补充 from the LEOR left sidebar: materials, functional zones, product display, meeting area, storage, screen, reception, and other details.
countinteger
Agent/MCP generation count. Must be 1. Multi-image generation is not enabled for Agent/MCP.
multiImageConfirmedboolean
Deprecated compatibility field. It does not enable multi-image generation in Agent/MCP.
countConfirmedboolean
Deprecated compatibility field. It does not enable multi-image generation in Agent/MCP.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name for generated assets.
renderModelstring
Public LEOR Chinese render model name: 快速渲染模型, 专业渲染模型, or 全能渲染模型. Use 专业渲染模型 by default. Do not pass real provider/model names.
resolutionstring
1K, 2K, or 4K. Use 1K for quick exploration, 2K for normal production, 4K only when requested.
aspectRatiostring
Image aspect ratio, default 16:9.
hasStorageboolean
Whether storage room is needed.
hasMeetingAreaboolean
Whether meeting area is needed.
logoUrlstring
Optional brand logo image URL. Strongly ask the user to upload a logo whenever possible because it improves brand accuracy.
logoImageBase64string
Optional brand logo image data URL from a local image attached in the current agent conversation. JPG/PNG/WEBP only, max 25MB.
logoBase64string
Alias of logoImageBase64.
logoAskedboolean
True only after you explicitly asked whether the user has a logo.
noLogoConfirmedboolean
True only when the user explicitly says they do not have a logo or will not provide it now.
sourceImageUrlstring
Optional reference image URL.
referenceImageBase64string
Optional reference image data URL from a local image attached in the current agent conversation. JPG/PNG/WEBP only, max 25MB.
sourceImageBase64string
Alias of referenceImageBase64.
referenceBase64string
Alias of referenceImageBase64.
referenceImageAskedboolean
True only after you explicitly asked whether the user has a reference image.
noReferenceConfirmedboolean
True only when the user explicitly says they do not have a reference image or will not provide it now.
galleryItemIdstring
Optional LEOR inspiration gallery item id. Prefer this over raw gallery image URLs when using a gallery image as reference.
briefConfirmedboolean
True only after you summarized the collected brief and the user explicitly confirmed generation.

evolve_booth_image

Refine an existing booth image by applying a user instruction such as 更科技, 更高端, 加洽谈区, 换材质, 加大屏, 强化门头. Use after the user selects a generated/reference image.

Parameters (4)

promptstringrequired
Change instruction, for example 更科技感 or 增加洽谈区.
sourceImageUrlstring
Current image URL.
exhibitItemIdstring
Optional LEOR canvas item id.
projectIdstring
Optional LEOR project id.

generate_storyboard

One-click LEOR node tool. Generate a 3x3 booth touring/storytelling storyboard from the current booth image. Use exact nodeToolMode storyboard for 展位分镜, 游览动线, 多角度展示, or client proposal visuals.

Parameters (5)

promptstring
Optional storyboard instruction. Keep it user-facing, for example 强调入口、洽谈区和产品体验动线.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

generate_material_board

One-click LEOR node tool. Generate a booth color/material board from the current booth image. Use exact nodeToolMode material_board for 材质看板, 色彩材质方案, construction direction, or proposal material direction.

Parameters (5)

promptstring
Optional material-board instruction. Keep it user-facing, for example 提取金属、玻璃、灯膜和主色彩体系.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

generate_everything_to_booth

One-click LEOR node tool. 万物成展 is for early-stage creative ideation: turn an arbitrary visual source, usually not an existing booth, into an exhibition booth concept by translating visual DNA such as color, shape, structure, material, lighting, and mood. Good sources include animals, fish, fruit, vegetables, logos, product photos, packaging, color swatches, textures, objects, and brand visuals. Do not use this as the normal tool for evolving an existing booth; use evolve_booth_image for booth changes, and use generate_booth_directions with galleryItemId/sourceImageUrl when a LEOR gallery booth is only a reference. Use exact nodeToolMode everything_to_booth for 万物成展.

Parameters (5)

promptstring
Optional direction instruction. Keep it user-facing, for example 提取这张图片的色彩和结构语言，转成科技展台方案.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

evolve_booth_image_with_image

Credit-consuming one-step image task. Use when the user sends an existing booth image and clearly asks to modify it. LEOR stores the source image in the user agent project, creates an output node, runs evolve, and returns a task id for polling. Requires one JPG/PNG/WEBP image up to 25MB and a clear change instruction. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Required change instruction, for example 把这张展位图改得更科技 or 加洽谈区.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_storyboard_with_image

Credit-consuming one-step image task. Use when the user sends a booth image and asks for 展位分镜, 游览动线, multi-angle storyboard, or proposal walkthrough. LEOR stores the source image in the user agent project, creates an output node, runs storyboard, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Optional storyboard instruction, for example 强调入口、洽谈区和产品体验动线.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_material_board_with_image

Credit-consuming one-step image task. Use when the user sends a booth image and asks for 材质看板, color/material board, or proposal material direction. LEOR stores the source image in the user agent project, creates an output node, runs material_board, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Optional material-board instruction, for example 提取金属、玻璃、灯膜和主色彩体系.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_everything_to_booth_with_image

Credit-consuming one-step image task. Use when the user sends an image and clearly wants to use that same image for 万物成展. Do not expose a separate upload step to the user. LEOR stores the source image in the user agent project, creates an output node, runs everything_to_booth, and returns a task id for polling. Accepts only one JPG/PNG/WEBP image up to 25MB, matching the main LEOR upload rules. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
User-facing direction, for example 用这张鱼的图片做万物成展.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_trend_poster_with_image

Credit-consuming one-step image task. Use when the user sends a booth image and asks for 潮流海报, KV-like booth promotion, or energetic proposal poster. LEOR stores the source image in the user agent project, creates an output node, runs trend_poster, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Optional poster instruction, for example 做成高冲击力科技新品发布会海报.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_minimal_poster_with_image

Credit-consuming one-step image task. Use when the user sends a booth image and asks for 简约海报, PPT cover, or restrained proposal cover. LEOR stores the source image in the user agent project, creates an output node, runs minimal_poster, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Optional poster instruction, for example 做成冷静高级的提案封面.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_glass_poster_with_image

Credit-consuming one-step image task. Use when the user sends a booth image and asks for 玻璃质感, premium archive cover, or restrained brand atmosphere poster. LEOR stores the source image in the user agent project, creates an output node, runs glass_poster, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

Parameters (5)

imageBase64stringrequired
User-provided image data URL. Must be JPG, PNG, or WEBP, max 25MB. This is consumed immediately by the selected LEOR task and is not a generic upload.
fileNamestring
Optional original file name, for example source.png.
promptstring
Optional poster instruction, for example 做成压花玻璃质感作品集封面.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name. If omitted, LEOR uses the user agent project.

generate_view_angle

Credit-consuming node tool. Generate one of LEOR’s 14 extra preset camera angles from an existing booth image. User-facing name: 旋转视角. Recognize older/synonym phrases such as 转换视角, 生成角度图, 换个角度, 多角度效果图, but reply to users with 旋转视角. Requires sourceImageUrl from a current LEOR image or visible image URL. Valid anglePreset values: left90_low, left90_eye, left90_top, left45_low, left45_eye, left45_top, front_low, front_top, right45_low, right45_eye, right45_top, right90_low, right90_eye, right90_top. Use right45_eye by default when the user only says 旋转视角. Poll with get_generation_result.

Parameters (8)

sourceImageUrlstring
Current booth image URL to transform into a new angle. Required before spending credits.
anglePresetstring
One of 14 LEOR preset extra angles: left90_low, left90_eye, left90_top, left45_low, left45_eye, left45_top, front_low, front_top, right45_low, right45_eye, right45_top, right90_low, right90_eye, right90_top. Use right45_eye by default.
rotateDegreesnumber
Legacy fallback only. LEOR snaps this to the nearest preset: -90, -45, 0, 45, or 90. Prefer anglePreset.
verticalTiltnumber
Legacy fallback only. LEOR snaps this to the nearest preset: -1 low angle, 0 eye level, 1 top-down. Prefer anglePreset.
promptstring
Optional user-facing angle instruction, for example 换成右前方45度, 来一张俯视角, 看左侧入口.
exhibitItemIdstring
Optional output LEOR canvas item id. Usually omit; LEOR can create one in the agent project.
projectIdstring
Optional existing LEOR project id.
projectNamestring
Optional project name for generated assets.

generate_trend_poster

One-click LEOR node tool. Generate a high-impact commercial proposal poster from the current booth image. Use exact nodeToolMode trend_poster for 潮流海报, KV-like booth promotion, social sharing, or energetic proposal visuals.

Parameters (5)

promptstring
Optional poster instruction. Keep it user-facing, for example 做成高冲击力科技新品发布会海报.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

generate_minimal_poster

One-click LEOR node tool. Generate a restrained high-end minimal proposal cover from the current booth image. Use exact nodeToolMode minimal_poster for 简约海报, PPT cover, client proposal title image, or quiet premium presentation visuals.

Parameters (5)

promptstring
Optional poster instruction. Keep it user-facing, for example 做成冷静高级的提案封面.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

generate_glass_poster

One-click LEOR node tool. Generate an embossed/frosted-glass portfolio-style cover from the current booth image. Use exact nodeToolMode glass_poster for 玻璃质感, premium archive cover, or restrained brand atmosphere image.

Parameters (5)

promptstring
Optional poster instruction. Keep it user-facing, for example 做成压花玻璃质感作品集封面.
sourceImageUrlstring
Image source URL. For view-angle/storyboard/material/poster tools this is usually the current LEOR booth image. For everything-to-booth this is usually an arbitrary non-booth visual source such as an animal, logo, fruit, color swatch, product, object, or texture. Required before spending credits; if missing, the tool returns needsMoreBrief.
exhibitItemIdstring
Optional LEOR canvas item id. Pass it when LEOR returned one so the result stays attached to the project.
projectIdstring
Optional LEOR project id. Pass it when LEOR returned one so the result is saved in that project.
projectNamestring
Optional project name for generated assets.

get_generation_result

Fetch task status and final result from LEOR by task id. Poll after generation until status is done or error, then return fullResUrl/image URLs and project/item ids when available. The progress number is an approximate LEOR stage indicator, not the real model-side completion percentage; it may jump between preparation, generation, saving, and done. In user-facing replies, prefer the message/status stage over exact percentages unless the user asks for technical status.

Parameters (1)

taskIdstringrequired
LEOR task id.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "leor-ai-booth-design-agent": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.leor.cn/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.