"Free and open-source GPS without an API" matching MCP servers:

Provides an OpenAI-compatible gateway to the MiMo (Xiaomi) model series, with native MCP server tools for web search and visual analysis.

OpenAI-compatible gateway and native MCP server for Xiaomi MiMo models, enabling search and vision capabilities in clients like Claude and Cursor.

Enables recognition and extraction of architectural CAD drawings (DWG) by creating tasks and retrieving structured results for frames, title blocks, and 23 building component types, including rooms, doors, windows, stairs, and text.

Enables AI agents to programmatically edit videos via FFmpeg, providing tools for probing, trimming, concatenating, timeline composition, LUT generation/application, rendering, and edit verification over MCP.

Enables small models to turn a short brief into complete HTML pages or looping GIFs with typography, palette, borders, motion, and validation already decided. It also lets agents list styles, retrieve style rules, create assets, validate HTML, and access reference examples.

Enables AI agents to generate images, videos, and lip-sync media, and to query wallet balances via the Open Generative Studio instance.

Enables AI assistants to control DaVinci Resolve (Free and Studio) through natural language, providing 162 tools for timeline editing, color grading, rendering, and more. Includes local AI replacements for Studio-only features like voice isolation, background removal, and transcription.

A zero-cost, China-accessible MCP server providing four free AI capabilities: text chat, image generation, speech-to-text, and text-to-speech, ready to use after cloning.

A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators, enabling metadata embedding, reading, validation, and report generation for lifestyle, product, and orbit schemas.

Provider-neutral Vision MCP Server — image analysis via 10 inference providers through a single MCP server.

Enables image and video generation using Luma's API, supporting multiple models, aspect ratios, and advanced features like keyframes and style references.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

Provides LLMs with full access to the Ken Video API for professional video processing, including adding audio, captions, and job management.

Exposes Open Video Guide functions to MCP clients, enabling conversion of tutorial videos into illustrated, verifiable guides with timestamps, evidence, and review states.

A server that integrates Blender with local AI models via the Model Context Protocol, allowing users to control Blender using natural language prompts for 3D modeling tasks.

Lets AI assistants and editors read documents on the local machine, turning PDFs, scans, invoices, receipts and bank statements into structured fields, line items and entities over stdio. Runs fully self-hosted with no cloud calls or API keys, so sensitive files never leave the user's machine.

Enables AI coding clients to generate and save project-aware images and videos using existing paid AI subscriptions, without API keys or passwords, and to optimize media for the web.

Enables AI agents to control a live Blender session for scene and object creation, modification, rendering, and PolyHaven asset workflows, while routing prompts through configurable local or remote LLM backends that can be switched at runtime.

Enables AI agents to control a live Blender session, manage scene objects and materials, render images, fetch PolyHaven assets, and send prompts to configurable local or OpenAI-compatible LLM providers with runtime switching.

Enables AI agents to inspect and modify live Blender scenes, manage objects and materials, render images, retrieve PolyHaven assets, and send prompts to configurable local or OpenAI-compatible LLM backends.