Thisispaper MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Thisispaper MCPFind concrete chapels in the Thisispaper archive"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Thisispaper MCP
Thisispaper is an independent art, architecture and design publication. Every project in the archive was curated by human editors since 2011.
Search 2,500+ curated projects: search, visual similarity, and full project metadata with material, light, mood and composition tags written during curation. Free tier, no signup to try.
Contact: studio@thisispaper.com
Endpoint (Streamable HTTP, stateless):
https://www.thisispaper.com/intelligence/api/mcpAuth: optional. Anonymous requests work out of the box (results capped at 5). A free self-serve key (200 calls/month) unlocks full results via
Authorization: Bearer tip_live_...
Tools
Tool | What it does |
| ChatGPT-connector search: results with id, title, url |
| ChatGPT-connector fetch: one project, full record, embeds the real thumbnail image |
| Ranked search across the archive: name, studio, city, year, category, intro, thumbnail, citation URL, provenance |
| Visually + semantically similar projects for a slug (precomputed SigLIP neighbours) |
| Full metadata for one project: description, design language, details, taste dimensions |
| Search by curation-time taste tags: material, light, color, mood, composition, subject |
| Newest projects, optionally by category (architecture, interiors, design, photography, art) |
| One project at random: editorial serendipity as a tool |
| Mints a free API key (200 calls/month) for an email address |
Every project-shaped response carries provenance (curated by, selection date, in archive since) and a permanent citation_url.
Related MCP server: Arke Institute MCP Server
Install
Cursor
Or add to .cursor/mcp.json:
{
"mcpServers": {
"thisispaper": {
"url": "https://www.thisispaper.com/intelligence/api/mcp"
}
}
}Gemini CLI
gemini extensions install https://github.com/zaxarovcom/thisispaper-mcpClaude Code
claude mcp add --transport http thisispaper https://www.thisispaper.com/intelligence/api/mcpClaude.ai (custom connector)
Settings → Connectors → Add custom connector → URL: https://www.thisispaper.com/intelligence/api/mcp
Any MCP client (generic)
Transport: Streamable HTTP. URL: https://www.thisispaper.com/intelligence/api/mcp. No OAuth. Optional header: Authorization: Bearer tip_live_...
Getting a free key
Ask the agent to call get_api_key with your email, or use the API docs page. 200 calls/month, no card.
Try it
"Find concrete chapels in the Thisispaper archive"
"Show me projects similar to audeum-kengo-kuma"
"What materials define Japanese teahouse projects?"
"Find projects with rammed earth and dusk light"About
Thisispaper is an independent art, architecture and design publication. Every project in the archive was curated by human editors since 2011.
Contact: studio@thisispaper.com
This server cannot be deployed
Maintenance
Related MCP Connectors
Personal asset search engine: everything you make or upload is searchable by what's inside it.
Search curated design styles, real product screens, and user flows for evidence-based design work.
Upload, organize, search, and transform images, videos, and files with AI-powered tools.
Automotive design reference search with filters, natural language, image retrieval, and comparison.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables programmatic access to the IACR Cryptology ePrint Archive, facilitating the search and retrieval of cryptographic research papers and metadata via a secure interface.33MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables semantic search across the Arke Institute's extensive archive of NARA records and presidential libraries using natural language queries. Provides access to millions of historical documents, photographs, and records with OCR'd content and complete metadata.-
- FlicenseNot gradedqualityDmaintenanceEnables searching and retrieving preserved Twitter data from the Community Archive, including user profiles, tweets, and keyword searches across archived content.-
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to index, search, and retrieve architectural documentation and store self-learning notes from codebases.1-