AI and Machine Learning Servers

Powerdrill

Official

Provides tools to interact with Powerdrill datasets to perform data work.

Real-time documentation context through vector-based search and retrieval via Qdrant.

Bridges multiple LLM providers including OpenAI, Anthropic, Google, DeepSeek, OpenRouter, and Ollama through a unified interface, enabling comparison of responses and leveraging specialized reasoning capabilities across different models.

Escalates complex reasoning tasks to more powerful language models (OpenAI o3, Google Gemini 2.5 Pro, DeepSeek Reasoner) by forwarding markdown prompts with code context and git diffs, returning responses with detailed cost tracking.

DeepL Translator

Official

Integrates with DeepL to provide high-quality text translation and rephrasing between numerous languages with formality controls for supported language pairs.

Provides cookie management capabilities for web automation and testing workflows, enabling storage, retrieval, and manipulation of session state and authentication cookies across different web services.

Provides image analysis capabilities through OpenRouter's vision models, supporting base64, file paths, and URLs with specialized tools for general analysis, webpage screenshot evaluation, and mobile app design assessment against platform guidelines.

Integrates with OpenAI's DALL-E 3 API to generate high-quality images with configurable size, quality, and style parameters, automatically saving results locally with descriptive filenames.

Manage, organize, and reuse prompt templates with variable substitution and multi-message conversation structures.

Provides dual-perspective analysis through alternating actor and critic viewpoints for evaluating creative works, strategic decisions, and complex scenarios requiring both empathetic understanding and objective assessment.

MiniMax Multimodal

Official

Official JavaScript implementation that integrates with MiniMax's multimodal capabilities for image generation, video creation, text-to-speech, and voice cloning across multiple transport modes.

Extracts content from diverse media sources including URLs, documents, videos, audio files, and images using intelligent auto-detection and multiple extraction engines for unified content processing and analysis.

Folderr

Official

Integrates with Folderr's API to enable management and communication with Folderr Assistants, facilitating tasks like listing assistants and sending questions.

Enables semantic search across multiple document collections using Qdrant vector database integration, allowing natural language queries with configurable result counts and collection tracking.

Integrates with Replicate's Flux image generation model, enabling image creation capabilities within conversation interfaces through a simple API token setup and TypeScript implementation available as both an npm module and Docker container.

Integrates multiple language models via the unified Unichat tool, enabling seamless interaction across OpenAI, MistralAI, Anthropic, xAI, and Google AI platforms.

ROS MCP Server

Official

Unlock true AI-powered robotics—control and observe any ROS1 or ROS2 robot using natural language. ROS-MCP-Server bridges large language models like Claude, GPT, and Gemini with your robot, enabling seamless two-way communication with zero changes to the robot’s code. Instantly browse topics, read sensors, call services, and adjust parameters—all through intuitive commands. Perfect for debugging, real-time control, and monitoring, this server works with both simulated and real robots and supports all MCP-compatible language models. Future updates will add enhanced permissions and action support for even greater flexibility.

Integrates with Octagon API to provide multi-source data aggregation, web scraping, academic research synthesis, competitive analysis, market intelligence, technical analysis, policy research, and trend analysis for professional-grade research capabilities.

Integrates with DeepSeek Thinker model to enable chain-of-thought reasoning and complex problem-solving for applications requiring advanced cognitive capabilities.

Integrates with Perspective API to analyze text toxicity and provide content moderation across multiple languages for enhanced online safety.

Generates images using Google's Gemini 2.5 Flash model and automatically uploads them to ImgBB, returning publicly accessible URLs for immediate web sharing without local file management.