"How to read PDFs and images" matching MCP servers:

Enriches Claude with tools to generate brand-consistent images using OpenAI's gpt-image-2 and upload them directly to Notion pages.

EasyAccessPDF is a production MCP server for PDF accessibility and document conversion. Five tools: convert documents (PDF/DOCX/PPT/XLS/HTML/EPUB/RTF/ODT/TXT) to clean Markdown; export PDFs to JSON/HTML/text/annotated-PDF; run veraPDF PDF/UA-1 (ISO 14289) accessibility audits with graded reports; auto-tag and remediate PDFs for WCAG 2.1/2.2, Section 508, ADA Title II and EAA/EN 301 549 compliance.

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.

MCP server for RenderForm API, enabling automatic generation of images, PDFs, screenshots, and videos from templates, along with management of renders, templates, fonts, and organization usage.

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

Enables AI agents to generate on-brand visuals from ideas, URLs, documents, or PDFs in over 100 formats and 150+ languages, with consistent brand kits.

Figma MCP server with full read/write access via plugin bridge — no API token, no rate limits. 58 tools for design automation: styles, variables, components, prototypes, and content.

MCP server for downloading images from Figma designs using access tokens. Supports multiple export formats and scale factors via a single tool.

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.

Enables AI assistants to generate images, videos, and PDFs from templates, manage templates, upload assets, organize folders, and access account usage through natural language.

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 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 AI agents to read .jww drawings, draw architectural elements like walls, openings, grids, and piping, and round-trip changes back into Jw_cad via DXF or 外部変形 batch bridges, plus convert scans and PDFs into layered CAD.

Enables AI agents to create and edit native KOMPAS-3D models from text descriptions, drawings, or PDFs, with parameterization, assemblies, drawings, and export to STEP, STL, and IGES.

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.