"Docker" matching MCP servers:

Enables private, GPU-backed image upscaling via a local Hermes MCP bridge that submits jobs to an authenticated Upscayl worker API.

MCP bridge for Kimi Code native AgentSwarm with inference through ai&. Supports authenticated Streamable HTTP MCP and Docker deployment.

Model Context Protocol (MCP) stdio server built with the official MCP Python SDK (FastMCP). Exposes 3 MCP tools: package_capability, generate_dockerfile, generate_claude_desktop_config — package AIMarket capabilities as Docker images + MCP manifest + Claude Desktop config. Entrypoint: mcp_stdio_server.py; root Dockerfile + glama.json in repo.

Enables Gemini-powered multimodal analysis (video, audio, image, documents), Google search, and code execution via the API易 service. Supports Docker deployment and flexible configuration.

MCP server for Langfuse that lets Claude Code create projects, manage API keys, and query traces without touching the web UI. Designed to work with a self-hosted Langfuse v3 stack running locally via Docker Compose.

Exposes infocepo.com infrastructure (LLM, ChromaDB, S3, Docker registry, service discovery) as MCP tools for AI agents.

MCP server for managing Ubuntu servers with AI integration, enabling system monitoring, Docker control, Gitea repository management, Ollama LLM interaction, workspace file operations, and Claude Code assistant via natural language.

MCP server for indexing and searching reaction-step-level synthesis routes from local SciFinder exports, designed for Docker/NAS deployment.

MCP server for predictalot, providing streamable HTTP tools for zero-shot time-series forecasting with multiple foundation models and per-type ensembles. Tabular ML endpoints are currently HTTP-only.

Adds image understanding to AI assistants that lack native vision, letting them analyze code screenshots, error captures, UI layouts, documents, and OCR content through a single unified image_understand tool. It routes requests across multiple vision model providers such as GLM-4.6V, DeepSeek-OCR, Qwen3-VL, Doubao-Seed, and Hunyuan, handling large-image cropping, compression, retries, and HTTP/Docker deployment.

Provides a unified image-understanding tool for AI coding assistants without native vision, letting them analyze screenshots, error messages, UI layouts, and documents through multiple vision LLM providers. Supports local files, remote URLs, and Data URIs with preprocessing, OCR, multi-crop, retries, and HTTP/Docker deployment.

Enables AI agents to manage a homelab by providing tools for Docker, Ollama, and system monitoring through the Model Context Protocol.

Enables AI coding clients that lack native vision to analyze screenshots of code, errors, UIs, and documents by routing images through a single image_understand tool backed by multiple vision LLM providers such as GLM-4.6V, DeepSeek-OCR, Qwen3-VL-Flash, Doubao-Seed, and Hunyuan-Vision. Handles local files, remote URLs, and Data URIs with automatic multi-crop, compression, retry, and OCR-friendly preprocessing, and can be deployed over stdio or shared HTTP/Docker for multiple clients.

Enables LLM agents to drive a self-hosted video toolkit through MCP tools, including lipsync, face restoration, ffmpeg operations, and metadata retrieval.

Enables AI clients and coding models without native vision to analyze images — screenshots, code errors, UI layouts, documents and OCR — through a single image_understand tool. Routes requests to multiple vision model providers with automatic preprocessing, multi-crop, compression, retry, and optional HTTP/Docker deployment for shared access.

A multi-model vision MCP server that gives image understanding to AI coding models lacking native vision, letting them analyze screenshots of code, errors, UI, and documents or perform OCR. It routes requests through major vision LLM providers and can be shared over local networks via HTTP or Docker.

Enables LLM agents to operate Cloud.ru MLSpace public API v2 through 17 action-based tools covering training, inference, notebooks, TensorBoards, workspaces, allocations, queues, Docker Registry, data transfer, and resource catalog, with read-only mode, dry-run, and confirmation gates for irreversible actions.

Generates technical documentation and diagrams (C4, UML, flowcharts, Gantt, etc.) using MCP protocol, with Docker-based tooling and optional AI image generation via DALL-E 3.

Enables AI coding assistants without native vision to analyze images such as screenshots, error messages, UI mockups, and documents through a single image_understand tool backed by multiple mainstream vision model providers. It handles local files, remote URLs, and Data URIs with automatic cropping, compression, and retries, and can be deployed locally via stdio or shared over HTTP/Docker.

This MCP server is a hot news aggregator and push assistant that supports AI analysis, multi-language translation, and rapid deployment via Docker or local setup.