mcpField
S
studiomcphub

studiomcphub

Remote
github.com/codex-curatorMedia & Design7Updated 4d ago
Repository

About studiomcphub

studiomcphub is an MCP server of creative AI tools and art datasets for autonomous agents, spanning image production, print preparation, and provenance workflows. It also provides search across more than 53,000 museum artworks in Alexandria Aeternum.

Key features

  1. 01Image generation and upscaling
  2. 02Background removal and product mockups
  3. 03CMYK conversion and print-ready PDFs
  4. 04SVG vectorization and invisible watermarking
  5. 05Metadata, provenance registration, and permanent storage
  6. 06Search a museum artwork dataset

Use cases

  1. 01Generate and upscale creative images
  2. 02Prepare product mockups and print files
  3. 03Add provenance details and verify artwork
  4. 04Find public-domain museum artworks

MCP support

It exposes 32 tools to MCP clients over a Streamable HTTP endpoint, including image processing, artwork search, and provenance operations. The README also describes per-call x402 USDC payments.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://studiomcphub.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

27
ParameterTypeRequiredDescription
imagestringYesBase64-encoded PNG/JPEG image
modelenumNoESRGAN model to use. Options: 'realesrgan_x2plus' (2x, general — default), 'realesrgan_x4plus' (4x, general/photo), 'realesrgan_x4plus_anime' (4x, anime/illustrations), 'realesr_general_x4v3' (4x, fast general), 'realesr_animevideov3' (4x, anime video frames).realesrgan_x2plus | realesrgan_x4plus | realesrgan_x4plus_anime | realesr_general_x4v3 | realesr_animevideov3
scaleintegerNoShorthand: 2 selects x2plus, 4 selects x4plus. Ignored if model is specified directly.

Details

From the project README

StudioMCPHub

Creative AI tools and art datasets for autonomous agents.

License: MIT MCP Glama StudioMCPHub on AI Agents Listing

StudioMCPHub is a production MCP server offering 32 tools (18 free): image generation, upscaling, background removal, product mockups, CMYK conversion, print-ready PDF, SVG vectorization, invisible watermarking, AI metadata enrichment, provenance registration, permanent Arweave storage, NFT minting, and access to 53,000+ museum artworks from Alexandria Aeternum. Agents pay per call with x402 USDC on Base L2 — no API keys, no accounts, no sign-up.

Quick Start

One-click install for Cursor:

Install in Cursor

Or add to any MCP client config:

{
  "mcpServers": {
    "studiomcphub": {
      "url": "https://studiomcphub.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Then call search_tools to discover available tools without loading all 32 schemas:

search_tools({ "category": "all" })

Tools

Discovery (FREE)
ToolDescription
search_toolsDiscover tools by category, price, or keyword (~98% token savings)
get_tool_schemaGet full JSON Schema + examples for a specific tool
Creative Pipeline
ToolPriceDescription
generate_image$0.20SD 3.5 Large text-to-image on NVIDIA L4 GPU
upscale_image$0.20Real-ESRGAN 4x super-resolution
enrich_metadata$0.20Gemini-powered 111-field Golden Codex analysis
infuse_metadata$0.10ExifTool XMP/IPTC/C2PA metadata embedding
register_hash$0.10256-bit perceptual hash with LSH band indexing
store_permanent$1.50Arweave L1 permanent immutable storage
mint_nft$1.00Polygon NFT with on-chain provenance link
verify_provenanceFREEPerceptual hash lookup against Aegis index
full_pipeline$0.50All stages in one call
Alexandria Aeternum Dataset

53,000+ public domain artworks from 7 world-class institutions.

ToolPriceDescription
search_artworksFREESearch by keyword, artist, period, or style
get_artwork$0.10Human-sourced metadata + signed image URL
get_artwork_oracle$0.20111-field NEST deep visual analysis
batch_download$5.00Bulk metadata + images (min 100)
compliance_manifestFREEAB 2013 + EU AI Act compliance docs

Payment

x402 (recommended for agents): Pay per call with USDC on Base L2. Server returns HTTP 402 with payment instructions. No account needed.

Stripe: Traditional card payment per call with API key.

GCX Credits: Pre-purchase tokens at volume discounts — $5 (50 GCX), $50 (600 GCX, 17% off), $100 (1600 GCX, 38% off).

Volume Discounts

Automatic per-wallet discounts based on 30-day rolling spend:

TierSpendDiscount
Standard$0–490%
Active$50–9910%
Pro$100–19920%
Studio$200+30%

Check your tier: GET https://studiomcphub.com/api/agent/tier/{wallet_address}

Loyalty

Every paid call earns 5% credit-back as loyalty GCX. No sign-up, no expiration.

Discovery Endpoints

EndpointDescription
https://studiomcphub.com/mcpMCP Streamable HTTP endpoint
https://studiomcphub.com/.well-known/mcp.jsonMCP server discovery
https://studiomcphub.com/.well-known/agent.jsonA2A Agent Card
https://studiomcphub.com/llms.txtLLM-readable documentation
https://studiomcphub.com/pricingPricing page

Self-Hosting

git clone https://github.com/codex-curator/studiomcphub.git
cd studiomcphub
pip install -r requirements.txt
# Set required environment variables (see .env.example)
gunicorn --bind 0.0.0.0:8080 --workers 2 --threads 4 src.mcp_server.server:app

Or with Docker:

docker build -t studiomcphub .
docker run -p 8080:8080 studiomcphub

Research

Alexandria Aeternum metadata density improves VLM visual perception by +25.5% and semantic coverage by +160.3%. See The Density Imperative.

Links

License

MIT — Metavolve Labs, Inc.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.