"How to work with local files" matching MCP servers:

A local, high-performance replacement for the hosted Figma MCP server that caches Figma files and exposes a local MCP endpoint for Cursor or any MCP client.

An MCP server that parses CAD files (.dwg, .dxf, .dwf, etc.) via the Cadlens API, enabling LLM clients to extract and reason over entity, layer, and metadata payloads.

Enables agents to create and edit Figma text using fonts installed locally on the user's computer, without uploading font files, through a local MCP bridge and companion Figma Desktop plugin.

Converts a Figma file into a React project using Ant Design, AG Grid, ApexCharts, and Tailwind CSS, with optional export of mobile screens as a React Native (Expo) app.

Enables AI agents to read and inspect local Figma .fig files entirely offline, exposing document structure, geometry, styles, text, components, variables, and embedded images via MCP tools.

Enables local control of Adobe After Effects via MCP, offering offline creative skills, project inspection, and operation execution without cloud relay or an installed AE panel.

A design harness for AI coding agents. Better Design gives an agent design systems, UI and UX principles, icons and UI review: it finds or creates a design system that fits the product and installs its components, explains how sign-up, forms and onboarding should work, and reviews finished screens for readability, accessibility and unclear copy.

Enables AI agents to read, create, edit, format, theme, preview and export Apple Numbers, Keynote and Pages files on macOS through 64 tools, including deck building from outlines, design kits, design review of slides, and Spotlight file lookup. Every write is backed up and swapped in atomically with one-call undo, and Arabic/RTL content round-trips exactly.

Extracts SVG icons from Figma and generates React TSX icon components automatically, enabling AI assistants like GitHub Copilot and Claude to manage icon workflows.

Provides read-only Figma design data to AI agents via MCP, supporting local .fig files and browser-based figma.com access without plugins or API tokens.

Enables AI assistants to access and work with Radix UI libraries (Themes, Primitives, Colors) by retrieving components, documentation, and installation guides through the Model Context Protocol.

A local MCP server that reads and edits a Figma Design file through a development plugin, creating real editable layers (frames, text, shapes, components, images) rather than flattened screenshots. It runs entirely on loopback with no personal access token, API key, or cloud bridge, letting an agent inspect documents, build and update layers, export previews, and wire up prototype navigation.

Enables AI agents to index TouchDesigner installations, control live instances with undoable batches and health checks, and inspect saved .toe projects offline.

Enables an agent to read, edit, and build Figma designs from scratch — including style guides, variables, components, and screens — through a local plugin bridge to the open file's Plugin API, with no Figma token or REST API calls.

Enables MCP clients to drive native CAD and 3D applications—Autodesk Fusion, Blender, and Unreal Engine—by planning work, executing trusted Python, inspecting real geometry, revising editable source files, and handing assets between applications. Each job keeps durable state, revision checks, and artifact hashes, with role-based handoffs for planning, modeling, geometry QA, interchange, and review.

Enables MCP clients to inspect FreeCAD documents and export named solids to STL, find and derive OrcaSlicer presets, preview and run slices with recorded manifests, and then read G-code metadata, query a Moonraker printer, upload G-code, and start an uploaded print as a separate confirmed step.

Converts Figma to Markdown. Strips out visual noise to drastically reduce LLM token consumption.

Lets AI clients drive a headless FreeCAD instance to build and inspect parts, check mass and interference, run finite element analyses, and produce drawings, bills of materials and export files. Every call returns numeric results and rendered PNG views so the model can verify its own work.

Enables controlling GIMP 3 locally through natural language, providing tools for image editing, layer management, selections, and PDB procedure invocation. Keeps all images and files on the user's machine with a local-first, secure design.

A local bridge that lets MCP clients inspect, export, and modify Figma files through a development Figma plugin.

Enables Cursor AI to read and modify Figma designs programmatically via the Model Context Protocol.

Enables AI agents to read and modify Figma designs programmatically through WebSocket communication, supporting document manipulation, styling, text replacement, and component management.

Enables local AI agents to generate and edit Figma designs via the Plugin API through a WebSocket relay, with no rate limits and all communication remaining local.

Enables AI assistants to read and modify Figma designs programmatically through the Model Context Protocol.

An MCP server that integrates AI agents with Figma, enabling reading and programmatic modification of designs.

Enables AI agents to directly control Figma Desktop via MCP, supporting UI creation, editing, prototyping, and variable management with over 60 tools.

Enables an MCP-compatible AI client to author Blender Python, run Blender, import the resulting asset into Unity with materials and a prefab, place it in the active scene, verify the import, and revise the same asset using stable IDs.

Enables generating CAD files through DXF drafting and OpenSCAD operations, with natural-language planning via local Ollama.

An MCP server that provides AI tools with relational tech principles, patterns, and the Studio library to guide builders in creating community-centered tools using embedded design.

This MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compatible clients.