Text To Model vs Figwright — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Text To Model vs Figwright
In-depth architectural comparison of the Text To Model and Figwright MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Text To Model
Architecture & Design · Remote HTTP/SSE
Quality: 47/100 (Fair) | Auth: No auth required
Figwright
Architecture & Design · Local stdio
Quality: 60/100 (Good) | Auth: No auth required
Verdict Summary: Choose Text To Model if you need specialized Architecture & Design tools running via a hosted cloud SSE transport. Choose Figwright if your workspace requires Architecture & Design integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Text To Model when:
You need dedicated capabilities in the Architecture & Design domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: 64 MCP tools for Fusion 360 CAD operations, Natural-language sketch and feature creation, JIS mechanical part generation.
Turn natural language into 3D models in Fusion 360. 64 CAD tools including sketches, extrudes, fillets, and JIS standard parts.
Bidirectional Figma server over a local WebSocket relay: turn a selection into framework-aware code (reusing your components and tokens), or author frames, text, styles, variables, and whole screens back onto the canvas. 92 tools, any MCP client, no Dev Mode seat or paid tier.
Category & Scope
Tools & Capabilities Breakdown
Text To Model Tools (6)
64 MCP tools for Fusion 360 CAD operations
Natural-language sketch and feature creation
JIS mechanical part generation
Parametric modeling and modification workflow
SVG and DXF import
STEP and STL export
Figwright Tools (3)
Read
selection, document and node inspection, styles, variables, components, fonts, reactions, motion (animation) state, screenshots, original image-fill assets, PDF export, and video export of animated frames (MP4 / GIF / WebM); plus `list_files` / `use_file` for working across more than one open Figma…
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Text To Model is categorized under Architecture & Design and uses a remote streaming HTTP/SSE transport. In contrast, Figwright belongs to Architecture & Design using local stdio subprocess. Select Text To Model when you need capabilities focused on architecture & design and Figwright when you require tools for architecture & design.
create and edit frames, text, shapes, auto-layout, effects, styles, variables, components (including authoring their boolean/text/instance-swap properties), pages, reactions, and Motion animations (keyframes, animation-style presets, timelines); plus a `batch` tool to apply many edits at once.
Grounding
`get_design_context` for faithful, de-duplicated design context, and `component_map` / `token_map` / `icon_map`, which join Figma data to your codebase so codegen reuses what you already have; plus `design_diff`, which reports what changed in a design against a saved baseline so you update only the…