{"id":"81ec4546-7535-43c2-b531-419069ea4ce9","entityType":"agent","slug":"clawhub-jau123-creative-toolkit","name":"Creative Toolkit","canonicalUrl":"https://www.xpersona.co/agent/clawhub-jau123-creative-toolkit","canonicalPath":"/agent/clawhub-jau123-creative-toolkit","generatedAt":"2026-10-09T14:53:40.431Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr... Skill: Creative Toolkit Owner: jau123 Summary: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-02-26T10:01:21.303Z | user Add semantic search to search_gallery - finds conceptually similar results via hybrid vector + keyword search v1.0.3 | 2026-02-19T13:47","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 463 downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn74jr6gzvvb4s6zv356hf8wnd812f14:creative-toolkit","sourceUrl":"https://clawhub.ai/jau123/creative-toolkit","homepage":"https://clawhub.ai/jau123/creative-toolkit","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/jau123/creative-toolkit","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":53,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":463,"packageName":null,"latestVersion":"1.0.4","tractionLabel":"463 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-03-01T05:36:01.473Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-03-01T05:36:01.473Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-02T05:36:01.473Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.4","createdAt":"2026-02-26T10:01:21.303Z","changelog":"Add semantic search to search_gallery - finds conceptually similar results via hybrid vector + keyword search","fileCount":2,"zipByteSize":4306},{"version":"1.0.3","createdAt":"2026-02-19T13:47:41.294Z","changelog":"Update description: replace FLUX/SDXL with Nanobanana Pro","fileCount":2,"zipByteSize":4170},{"version":"1.0.2","createdAt":"2026-02-16T12:27:26.346Z","changelog":"Add Security & Privacy section documenting remote execution, image upload, token handling, and no-telemetry policy","fileCount":null,"zipByteSize":null},{"version":"1.0.1","createdAt":"2026-02-14T00:32:01.671Z","changelog":"Fix homepage URL","fileCount":null,"zipByteSize":null},{"version":"1.0.0","createdAt":"2026-02-13T11:50:43.866Z","changelog":"Multi-provider AI image generation MCP server with curated prompt library and style-aware enhancement","fileCount":null,"zipByteSize":null}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn74jr6gzvvb4s6zv356hf8wnd812f14:creative-toolkit","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T14:53:40.431Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jau123-creative-toolkit/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Creative Toolkit\n\nOwner: jau123\n\nSummary: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr...\n\nTags: latest:1.0.4\n\nVersion history:\n\nv1.0.4 | 2026-02-26T10:01:21.303Z | user\n\nAdd semantic search to search_gallery - finds conceptually similar results via hybrid vector + keyword search\n\nv1.0.3 | 2026-02-19T13:47:41.294Z | user\n\nUpdate description: replace FLUX/SDXL with Nanobanana Pro\n\nv1.0.2 | 2026-02-16T12:27:26.346Z | user\n\nAdd Security & Privacy section documenting remote execution, image upload, token handling, and no-telemetry policy\n\nv1.0.1 | 2026-02-14T00:32:01.671Z | user\n\nFix homepage URL\n\nv1.0.0 | 2026-02-13T11:50:43.866Z | user\n\nMulti-provider AI image generation MCP server with curated prompt library and style-aware enhancement\n\nArchive index:\n\nArchive v1.0.4: 2 files, 4306 bytes\n\nFiles: SKILL.md (9220b), _meta.json (135b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: creative-toolkit\ndescription: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.\nversion: 1.0.4\nhomepage: https://github.com/jau123/MeiGen-AI-Design-MCP\nmetadata: {\"clawdbot\":{\"emoji\":\"🎨\",\"requires\":{\"bins\":[\"mcporter\"],\"env\":[\"MEIGEN_API_TOKEN\"]},\"primaryEnv\":\"MEIGEN_API_TOKEN\"}}\n---\n\n# Creative Toolkit\n\nGenerate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.\n\n## Quick Start\n\nAdd the MCP server to your mcporter config (`~/.config/mcporter/config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@latest\"],\n      \"env\": {\n        \"MEIGEN_API_TOKEN\": \"${MEIGEN_API_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\nSet your API token in `~/.clawdbot/.env` or shell environment:\n\n```bash\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nGenerate your first image:\n\n```bash\nmcporter call creative-toolkit.generate_image prompt=\"a minimalist perfume bottle on white marble, soft directional lighting, product photography\"\n```\n\nOr try it without any config (ad-hoc stdio mode):\n\n```bash\nmcporter call --stdio \"npx -y meigen@latest\" generate_image prompt=\"a ceramic vase with morning light\"\n```\n\nNo API key? Free tools still work:\n\n```bash\nmcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\"\n```\n\n## Setup\n\n### Get an API Token\n\n1. Visit [meigen.ai](https://www.meigen.ai) → sign in → click avatar → **Settings** → **API Keys**\n2. Create a new key (starts with `meigen_sk_`)\n3. Set as environment variable or save to config:\n\n```bash\n# Shell environment or ~/.clawdbot/.env\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nOr save to `~/.config/meigen/config.json`:\n\n```json\n{\n  \"meigenApiToken\": \"meigen_sk_...\"\n}\n```\n\n### Alternative Providers\n\nYou can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default provider. Save to `~/.config/meigen/config.json`:\n\n**OpenAI / Together AI / Fireworks AI:**\n\n```json\n{\n  \"openaiApiKey\": \"sk-...\",\n  \"openaiBaseUrl\": \"https://api.together.xyz/v1\",\n  \"openaiModel\": \"black-forest-labs/FLUX.1-schnell\"\n}\n```\n\n**Local ComfyUI:**\n\n```json\n{\n  \"comfyuiUrl\": \"http://localhost:8188\"\n}\n```\n\nImport workflows with the `comfyui_workflow` tool (action: `import`). The server auto-detects key nodes (KSampler, CLIPTextEncode, EmptyLatentImage) and fills in prompt, seed, and dimensions at runtime.\n\nMultiple providers can be configured simultaneously. Auto-detection priority: MeiGen > ComfyUI > OpenAI.\n\n## Available Tools\n\n### Free — no API key required\n\n| Tool | What it does |\n|------|-------------|\n| `search_gallery` | Semantic search across AI image prompts — finds conceptually similar results, not just keyword matches. Also supports category filtering and curated browsing. Returns prompt text, thumbnails, and metadata. |\n| `get_inspiration` | Get the full prompt and high-res images for any gallery entry. Use after `search_gallery` to get copyable prompts. |\n| `enhance_prompt` | Expand a brief idea (e.g. \"a cat in space\") into a detailed, style-aware prompt with lighting, composition, and material directions. Supports three styles: realistic, anime, illustration. |\n| `list_models` | List all available models across configured providers with capabilities and supported features. |\n\n### Requires configured provider\n\n| Tool | What it does |\n|------|-------------|\n| `generate_image` | Generate an image from a text prompt. Automatically routes to the best available provider. Supports aspect ratio, seed, and reference images. |\n| `upload_reference_image` | Compress and upload a local image (max 2MB, 2048px) for use as a style reference in generation. Returns a public URL. |\n| `comfyui_workflow` | List, view, import, modify, and delete ComfyUI workflow templates. Modify parameters like steps, CFG scale, sampler, and checkpoint without editing JSON. |\n\n## Usage Patterns\n\n### Basic generation\n\n```\nGenerate a product photo of a ceramic vase with morning light\n```\n\nThe server picks the best provider, generates the image, and returns a URL + local file path.\n\n### Prompt enhancement then generation\n\nFor brief ideas, enhance first for much better results:\n\n```\n1. enhance_prompt brief=\"futuristic city\" style=\"realistic\"\n   → Returns detailed prompt with camera lens, lighting setup, atmospheric effects\n\n2. generate_image prompt=\"<enhanced prompt>\" aspectRatio=\"16:9\"\n   → Generates with the enhanced prompt\n```\n\n### Reference image workflow\n\nUse an existing image to guide style and composition:\n\n```\n1. upload_reference_image filePath=\"~/Desktop/my-logo.png\"\n   → Returns public URL\n\n2. generate_image prompt=\"coffee mug mockup with this logo\" referenceImages=[\"<url>\"]\n   → Generates using the reference for style guidance\n```\n\nReference images work across all providers.\n\n### Gallery exploration\n\nSemantic search understands intent — \"dreamy portrait with soft light\" finds relevant results even without exact keyword matches:\n\n```\n1. search_gallery query=\"dreamy portrait with soft light\"\n   → Finds semantically similar prompts with thumbnails\n\n2. search_gallery category=\"Product\"\n   → Browse by category from 1,300+ curated prompts\n\n3. get_inspiration id=\"<entry_id>\"\n   → Get full prompt text — copy and modify for your own generation\n```\n\n### ComfyUI workflows\n\n```\n1. comfyui_workflow action=\"list\"\n   → See saved workflows\n\n2. comfyui_workflow action=\"view\" name=\"txt2img\"\n   → See adjustable parameters (steps, CFG, sampler, checkpoint)\n\n3. comfyui_workflow action=\"modify\" name=\"txt2img\" modifications={\"steps\": 30, \"cfg\": 7.5}\n   → Adjust without editing JSON\n\n4. generate_image prompt=\"...\" workflow=\"txt2img\"\n   → Generate using the custom workflow\n```\n\n## Provider Comparison\n\n| | MeiGen Platform | OpenAI-Compatible | ComfyUI (Local) |\n|---|---|---|---|\n| **Models** | Nanobanana Pro, GPT Image 1.5, Seedream 4.5, etc. | Any model at the endpoint | Any checkpoint on your machine |\n| **Reference images** | Native support | gpt-image-1.5 only | Requires LoadImage node |\n| **Concurrency** | Up to 4 parallel | Up to 4 parallel | 1 at a time (GPU constraint) |\n| **Latency** | 10-30s typical | Varies by provider | Depends on hardware |\n| **Cost** | Token-based credits | Provider billing | Free (your hardware) |\n| **Offline** | No | No | Yes |\n\n## Prompt Enhancement Styles\n\n`enhance_prompt` supports three style modes, each producing different types of detail:\n\n| Style | Focus | Best For |\n|-------|-------|----------|\n| `realistic` | Camera lens, aperture, focal length, lighting direction, material textures | Product photos, portraits, architecture |\n| `anime` | Key visual composition, character details (eyes, hair, costume), trigger words | Anime illustrations, character design |\n| `illustration` | Art medium, color palette, composition direction, brush texture | Concept art, digital painting, watercolor |\n\n## Security & Privacy\n\n**Remote package execution**: This skill runs as an MCP server via `npx meigen@latest`. The package is published on [npmjs.com](https://www.npmjs.com/package/meigen) under the `meigen` name with full source code available at [GitHub](https://github.com/jau123/MeiGen-AI-Design-MCP). No code is obfuscated or minified beyond standard TypeScript compilation.\n\n**Reference image upload**: The `upload_reference_image` tool compresses local images (max 2MB, 2048px) and uploads them to a CDN for use as generation references. This is always user-initiated — the tool never accesses or uploads files without explicit invocation. Uploaded images are used solely as style references for image generation.\n\n**API tokens**: `MEIGEN_API_TOKEN` is stored locally in environment variables or `~/.config/meigen/config.json` with `chmod 600` permissions. Tokens are only sent to the configured provider's API endpoint and never logged or transmitted elsewhere.\n\n**No telemetry**: The MCP server does not collect analytics, usage data, or send any information to third parties beyond the configured image generation provider.\n\n## Troubleshooting\n\n**\"No image generation providers configured\"**\n→ Set `MEIGEN_API_TOKEN` or configure an alternative provider in `~/.config/meigen/config.json`\n\n**Timeout during generation**\n→ Image generation typically takes 10-30 seconds. During high demand, it may take longer. The server polls with a 5-minute timeout.\n\n**ComfyUI connection refused**\n→ Ensure ComfyUI is running and accessible at the configured URL. Test with: `curl <url>/system_stats`\n\n**\"Model not found\"**\n→ Run `list_models` to see available models for your configured providers.\n\n**Reference image rejected**\n→ Images must be public URLs (not local paths). Use `upload_reference_image` to convert local files to URLs first.\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn74jr6gzvvb4s6zv356hf8wnd812f14\",\n  \"slug\": \"creative-toolkit\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1772100081303\n}\n\nArchive v1.0.3: 2 files, 4170 bytes\n\nFiles: SKILL.md (8882b), _meta.json (135b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: creative-toolkit\ndescription: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.\nversion: 1.0.3\nhomepage: https://github.com/jau123/MeiGen-AI-Design-MCP\nmetadata: {\"clawdbot\":{\"emoji\":\"🎨\",\"requires\":{\"bins\":[\"mcporter\"],\"env\":[\"MEIGEN_API_TOKEN\"]},\"primaryEnv\":\"MEIGEN_API_TOKEN\"}}\n---\n\n# Creative Toolkit\n\nGenerate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.\n\n## Quick Start\n\nAdd the MCP server to your mcporter config (`~/.config/mcporter/config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@latest\"],\n      \"env\": {\n        \"MEIGEN_API_TOKEN\": \"${MEIGEN_API_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\nSet your API token in `~/.clawdbot/.env` or shell environment:\n\n```bash\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nGenerate your first image:\n\n```bash\nmcporter call creative-toolkit.generate_image prompt=\"a minimalist perfume bottle on white marble, soft directional lighting, product photography\"\n```\n\nOr try it without any config (ad-hoc stdio mode):\n\n```bash\nmcporter call --stdio \"npx -y meigen@latest\" generate_image prompt=\"a ceramic vase with morning light\"\n```\n\nNo API key? Free tools still work:\n\n```bash\nmcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\"\n```\n\n## Setup\n\n### Get an API Token\n\n1. Visit [meigen.ai](https://www.meigen.ai) → sign in → click avatar → **Settings** → **API Keys**\n2. Create a new key (starts with `meigen_sk_`)\n3. Set as environment variable or save to config:\n\n```bash\n# Shell environment or ~/.clawdbot/.env\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nOr save to `~/.config/meigen/config.json`:\n\n```json\n{\n  \"meigenApiToken\": \"meigen_sk_...\"\n}\n```\n\n### Alternative Providers\n\nYou can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default provider. Save to `~/.config/meigen/config.json`:\n\n**OpenAI / Together AI / Fireworks AI:**\n\n```json\n{\n  \"openaiApiKey\": \"sk-...\",\n  \"openaiBaseUrl\": \"https://api.together.xyz/v1\",\n  \"openaiModel\": \"black-forest-labs/FLUX.1-schnell\"\n}\n```\n\n**Local ComfyUI:**\n\n```json\n{\n  \"comfyuiUrl\": \"http://localhost:8188\"\n}\n```\n\nImport workflows with the `comfyui_workflow` tool (action: `import`). The server auto-detects key nodes (KSampler, CLIPTextEncode, EmptyLatentImage) and fills in prompt, seed, and dimensions at runtime.\n\nMultiple providers can be configured simultaneously. Auto-detection priority: MeiGen > ComfyUI > OpenAI.\n\n## Available Tools\n\n### Free — no API key required\n\n| Tool | What it does |\n|------|-------------|\n| `search_gallery` | Search 1,300+ curated prompts by keyword, style, or category. Returns prompt text, thumbnails, and metadata. |\n| `get_inspiration` | Get the full prompt and high-res images for any gallery entry. Use after `search_gallery` to get copyable prompts. |\n| `enhance_prompt` | Expand a brief idea (e.g. \"a cat in space\") into a detailed, style-aware prompt with lighting, composition, and material directions. Supports three styles: realistic, anime, illustration. |\n| `list_models` | List all available models across configured providers with capabilities and supported features. |\n\n### Requires configured provider\n\n| Tool | What it does |\n|------|-------------|\n| `generate_image` | Generate an image from a text prompt. Automatically routes to the best available provider. Supports aspect ratio, seed, and reference images. |\n| `upload_reference_image` | Compress and upload a local image (max 2MB, 2048px) for use as a style reference in generation. Returns a public URL. |\n| `comfyui_workflow` | List, view, import, modify, and delete ComfyUI workflow templates. Modify parameters like steps, CFG scale, sampler, and checkpoint without editing JSON. |\n\n## Usage Patterns\n\n### Basic generation\n\n```\nGenerate a product photo of a ceramic vase with morning light\n```\n\nThe server picks the best provider, generates the image, and returns a URL + local file path.\n\n### Prompt enhancement then generation\n\nFor brief ideas, enhance first for much better results:\n\n```\n1. enhance_prompt brief=\"futuristic city\" style=\"realistic\"\n   → Returns detailed prompt with camera lens, lighting setup, atmospheric effects\n\n2. generate_image prompt=\"<enhanced prompt>\" aspectRatio=\"16:9\"\n   → Generates with the enhanced prompt\n```\n\n### Reference image workflow\n\nUse an existing image to guide style and composition:\n\n```\n1. upload_reference_image filePath=\"~/Desktop/my-logo.png\"\n   → Returns public URL\n\n2. generate_image prompt=\"coffee mug mockup with this logo\" referenceImages=[\"<url>\"]\n   → Generates using the reference for style guidance\n```\n\nReference images work across all providers.\n\n### Gallery exploration\n\n```\n1. search_gallery query=\"product photography\" category=\"Product\"\n   → Browse thumbnails and prompts\n\n2. get_inspiration id=\"<entry_id>\"\n   → Get full prompt text — copy and modify for your own generation\n```\n\n### ComfyUI workflows\n\n```\n1. comfyui_workflow action=\"list\"\n   → See saved workflows\n\n2. comfyui_workflow action=\"view\" name=\"txt2img\"\n   → See adjustable parameters (steps, CFG, sampler, checkpoint)\n\n3. comfyui_workflow action=\"modify\" name=\"txt2img\" modifications={\"steps\": 30, \"cfg\": 7.5}\n   → Adjust without editing JSON\n\n4. generate_image prompt=\"...\" workflow=\"txt2img\"\n   → Generate using the custom workflow\n```\n\n## Provider Comparison\n\n| | MeiGen Platform | OpenAI-Compatible | ComfyUI (Local) |\n|---|---|---|---|\n| **Models** | Nanobanana Pro, GPT Image 1.5, Seedream 4.5, etc. | Any model at the endpoint | Any checkpoint on your machine |\n| **Reference images** | Native support | gpt-image-1.5 only | Requires LoadImage node |\n| **Concurrency** | Up to 4 parallel | Up to 4 parallel | 1 at a time (GPU constraint) |\n| **Latency** | 10-30s typical | Varies by provider | Depends on hardware |\n| **Cost** | Token-based credits | Provider billing | Free (your hardware) |\n| **Offline** | No | No | Yes |\n\n## Prompt Enhancement Styles\n\n`enhance_prompt` supports three style modes, each producing different types of detail:\n\n| Style | Focus | Best For |\n|-------|-------|----------|\n| `realistic` | Camera lens, aperture, focal length, lighting direction, material textures | Product photos, portraits, architecture |\n| `anime` | Key visual composition, character details (eyes, hair, costume), trigger words | Anime illustrations, character design |\n| `illustration` | Art medium, color palette, composition direction, brush texture | Concept art, digital painting, watercolor |\n\n## Security & Privacy\n\n**Remote package execution**: This skill runs as an MCP server via `npx meigen@latest`. The package is published on [npmjs.com](https://www.npmjs.com/package/meigen) under the `meigen` name with full source code available at [GitHub](https://github.com/jau123/MeiGen-AI-Design-MCP). No code is obfuscated or minified beyond standard TypeScript compilation.\n\n**Reference image upload**: The `upload_reference_image` tool compresses local images (max 2MB, 2048px) and uploads them to a CDN for use as generation references. This is always user-initiated — the tool never accesses or uploads files without explicit invocation. Uploaded images are used solely as style references for image generation.\n\n**API tokens**: `MEIGEN_API_TOKEN` is stored locally in environment variables or `~/.config/meigen/config.json` with `chmod 600` permissions. Tokens are only sent to the configured provider's API endpoint and never logged or transmitted elsewhere.\n\n**No telemetry**: The MCP server does not collect analytics, usage data, or send any information to third parties beyond the configured image generation provider.\n\n## Troubleshooting\n\n**\"No image generation providers configured\"**\n→ Set `MEIGEN_API_TOKEN` or configure an alternative provider in `~/.config/meigen/config.json`\n\n**Timeout during generation**\n→ Image generation typically takes 10-30 seconds. During high demand, it may take longer. The server polls with a 5-minute timeout.\n\n**ComfyUI connection refused**\n→ Ensure ComfyUI is running and accessible at the configured URL. Test with: `curl <url>/system_stats`\n\n**\"Model not found\"**\n→ Run `list_models` to see available models for your configured providers.\n\n**Reference image rejected**\n→ Images must be public URLs (not local paths). Use `upload_reference_image` to convert local files to URLs first.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn74jr6gzvvb4s6zv356hf8wnd812f14\",\n  \"slug\": \"creative-toolkit\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1771508861294\n}","readmeExcerpt":"Skill: Creative Toolkit Owner: jau123 Summary: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-02-26T10:01:21.303Z | user Add semantic search to search_gallery - finds conceptually similar results via hybrid vector + keyword search v1.0.3 | 2026-02-19T13:47","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@latest\"],\n      \"env\": {\n        \"MEIGEN_API_TOKEN\": \"${MEIGEN_API_TOKEN}\"\n      }\n    }\n  }\n}"},{"language":"bash","snippet":"export MEIGEN_API_TOKEN=\"meigen_sk_...\""},{"language":"bash","snippet":"mcporter call creative-toolkit.generate_image prompt=\"a minimalist perfume bottle on white marble, soft directional lighting, product photography\""},{"language":"bash","snippet":"mcporter call --stdio \"npx -y meigen@latest\" generate_image prompt=\"a ceramic vase with morning light\""},{"language":"bash","snippet":"mcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\""},{"language":"bash","snippet":"# Shell environment or ~/.clawdbot/.env\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: creative-toolkit\ndescription: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.\nversion: 1.0.4\nhomepage: https://github.com/jau123/MeiGen-AI-Design-MCP\nmetadata: {\"clawdbot\":{\"emoji\":\"🎨\",\"requires\":{\"bins\":[\"mcporter\"],\"env\":[\"MEIGEN_API_TOKEN\"]},\"primaryEnv\":\"MEIGEN_API_TOKEN\"}}\n---\n\n# Creative Toolkit\n\nGenerate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.\n\n## Quick Start\n\nAdd the MCP server to your mcporter config (`~/.config/mcporter/config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@latest\"],\n      \"env\": {\n        \"MEIGEN_API_TOKEN\": \"${MEIGEN_API_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\nSet your API token in `~/.clawdbot/.env` or shell environment:\n\n```bash\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nGenerate your first image:\n\n```bash\nmcporter call creative-toolkit.generate_image prompt=\"a minimalist perfume bottle on white marble, soft directional lighting, product photography\"\n```\n\nOr try it without any config (ad-hoc stdio mode):\n\n```bash\nmcporter call --stdio \"npx -y meigen@latest\" generate_image prompt=\"a ceramic vase with morning light\"\n```\n\nNo API key? Free tools still work:\n\n```bash\nmcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\"\n```\n\n## Setup\n\n### Get an API Token\n\n1. Visit [meigen.ai](https://www.meigen.ai) → sign in → click avatar → **Settings** → **API Keys**\n2. Create a new key (starts with `meigen_sk_`)\n3. Set as environment variable or save to config:\n\n```bash\n# Shell environment or ~/.clawdbot/.env\nexport MEIGEN_API_TOKEN=\"meigen_sk_...\"\n```\n\nOr save to `~/.config/meigen/config.json`:\n\n```json\n{\n  \"meigenApiToken\": \"meigen_sk_...\"\n}\n```\n\n### Alternative Providers\n\nYou can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default provider. Save to `~/.config/meigen/config.json`:\n\n**OpenAI / Together AI / Fireworks AI:**\n\n```json\n{\n  \"openaiApiKey\": \"sk-...\",\n  \"openaiBaseUrl\": \"https://api.together.xyz/v1\",\n  \"openaiModel\": \"black-forest-labs/FLUX.1-schnell\"\n}\n```\n\n**Local ComfyUI:**\n\n```json\n{\n  \"comfyuiUrl\": \"http://localhost:8188\"\n}\n```\n\nImport workflows with the `comfyui_workflow` tool (action: `import`). The server auto-detects key nodes (KSampler, CLIPTextEncode, EmptyLatentImage) and fills in prompt, seed, and dimensions at runtime.\n\nMultiple providers can be configured simultaneously. Auto-detection priority: MeiGen > ComfyUI > OpenAI.\n\n## Available Tools\n\n### Free — no AP"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn74jr6gzvvb4s6zv356hf8wnd812f14\",\n  \"slug\": \"creative-toolkit\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1772100081303\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr... Skill: Creative Toolkit Owner: jau123 Summary: Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated pr... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-02-26T10:01:21.303Z | user Add semantic search to search_gallery - finds conceptually similar results via hybrid vector + keyword search v1.0.3 | 2026-02-19T13:47","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":714,"uniquenessScore":59,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T14:53:40.431Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}