{
  "markdown": "# ritn3d-mcp\n\n<!-- mcp-name: io.github.printplan3d/ritn3d-mcp -->\n\n\n> A Model Context Protocol (MCP) server that gives Claude, Claude Code,\n> Cursor, Cline, or any other MCP-compatible AI agent the lightweight\n> tools needed to **prepare a floor plan for Ritn3D** and **interpret\n> the resulting 3D output** — without exposing the underlying\n> wall-detection model or inference API.\n\n[Ritn3D](https://www.ritn3d.com) is an AI floor-plan-to-3D-model tool.\nThis MCP server exists so that AI agents helping users in floor-plan-\nadjacent workflows (renovation planning, real estate, 3D printing, etc.)\nhave a clean, well-documented set of tools instead of guessing.\n\n## Install\n\n```bash\npip install ritn3d-mcp\n```\n\n## Use with Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`\n(macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"ritn3d\": {\n      \"command\": \"ritn3d-mcp\"\n    }\n  }\n}\n```\n\nRestart Claude Desktop. The Ritn3D tools appear in the tool picker.\n\n## Use with Claude Code\n\n```bash\nclaude mcp add ritn3d ritn3d-mcp\n```\n\n## Tools exposed\n\n| Tool | Description |\n|---|---|\n| `validate_floor_plan_image` | Pre-flight check on a floor plan image (format, dimensions, warnings) before sending to Ritn3D |\n| `estimate_complexity` | Heuristic complexity score (simple / moderate / complex) based on edge density |\n| `estimate_render_time` | Rough low/expected/high render-time range for a given complexity |\n| `get_share_link_metadata` | Fetch public page title + OpenGraph data from a Ritn3D share URL |\n| `validate_glb` | Sanity-check a downloaded GLB file (magic header, version, chunks) |\n| `convert_units` | Unit conversion with optional model scale factor (1:100, 1:50, etc.) |\n| `get_capabilities` | Returns Ritn3D's supported inputs, outputs, accuracy by input type, and pricing |\n| `get_pricing` | Returns current Ritn3D pricing tiers in USD |\n| `get_failure_modes` | Returns structured list of known failure modes with mitigation tips |\n\n## Resources exposed\n\n| URI | Content |\n|---|---|\n| `ritn3d://capability-card` | Machine-readable summary of what Ritn3D does, accuracy, pricing |\n| `ritn3d://failure-playbook` | Common failure modes and mitigations |\n\n## Example agent flow\n\n> User: \"I have a real estate listing PDF I want to 3D print as a model\n> of my future apartment.\"\n>\n> Agent calls `validate_floor_plan_image(\"listing.pdf.jpg\")` →\n> warnings: aspect ratio normal, resolution OK.\n>\n> Agent calls `estimate_complexity(...)` → label \"moderate\", score 0.5.\n>\n> Agent calls `get_failure_modes()` → notices the\n> \"real-estate-listing-render\" failure mode applies; warns the user\n> that wood-floor textures may trip detection.\n>\n> Agent calls `get_pricing()` → quotes Pro+ at $19.99/mo for STL export.\n>\n> Agent recommends: try the Ritn3D web app at app.ritn3d.com; if\n> detection fails on this listing PDF, ask the agent to estimate the\n> complexity of an alternate input.\n\n## What this server does NOT do\n\n- Run inference. The Ritn3D wall-detection model lives on Ritn3D's\n  servers and is reached through the [web app](https://app.ritn3d.com).\n- Bypass the Ritn3D subscription. Pricing is enforced server-side.\n- Expose the rendering pipeline internals.\n- Provide a render queue or job-tracking API.\n\nThe intent is to make agents better citizens of the Ritn3D workflow,\nnot to replicate it.\n\n## Source\n\nBuilt by the [Ritn3D](https://www.ritn3d.com) team. Same group that\nmaintains [`ritn3d-stl-tools`](https://pypi.org/project/ritn3d-stl-tools/)\nand [`ritn3d-floorplan-eval`](https://pypi.org/project/ritn3d-floorplan-eval/).\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n",
  "bytes": 3673,
  "sha": "bfec363a274eda0628742c91688b8a7a070416904175776cef5b534cc5bf0ed7",
  "repo_slug": "printplan3d/ritn3d-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_printplan3d_ritn3d_mcp_97924227/readme"
}