Replicate is a platform that lets you run machine learning models with a cloud API, without having to understand the underlying infrastructure or manage your own servers.
Enables AI assistants to generate images, videos, music, and voiceovers with your own provider keys, and edit video locally with ffmpeg — all on your machine with no account, watermark, or telemetry.
35
33 npm
MIT
Why this server?
Auto-detects webhooks from Replicate AI provider, extracts job ID, status, and prediction time information, and correlates them into pipeline traces for monitoring AI model inferences.
Self-hosted webhook relay and tunnel with Noise NK encryption. Inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels — 13 MCP tools. No tokens or passwords needed.
13
8
AGPL 3.0
Why this server?
Integrates with Replicate API for generating images, music, and videos using various models.
Local MCP server that plans, generates, and assembles production assets (images, audio, video) through multi-agent personas and official APIs, with free-tier budget guard.
Enables AI agents to scan text for leaked secrets and prompt injection markers, and redact them before reaching an LLM.
2
1
MIT
Why this server?
Enables text-to-video generation via the Replicate API, including starting a video generation from a prompt (optionally with a first-frame image), checking generation status by ID, and downloading finished videos to disk. Supports the minimax/video-01 model by default and any Replicate video model that accepts a prompt input.
Enables Claude to generate videos from text prompts via the Replicate API, check generation status, and download completed videos to disk.
3
MIT
Why this server?
Runs any Replicate model (diffusion, pixel-art animation, video) using your sprite as input; can list a model's inputs, render the sprite upscaled on a solid background for the model's image input, and run one prediction per prompt, then pipes the raw outputs into the ingest pipeline to be cleaned into pixel art.
Enables AI assistants to draw, animate, and export game-ready pixel art and sprite sheets through a local Aseprite installation, including palette work, layer rigging, and cleanup of AI-generated frames. It also offers a CLI for running the same animation recipes in a game asset pipeline.
17
91 npm
MIT
Why this server?
Provides access to the ideogram-ai/ideogram-v3-balanced image generation model via Replicate, enabling text-to-image generation, inpainting, style transfer with 60+ artistic presets, and support for 15 aspect ratios and 65+ custom resolutions.
Enables AI-powered image generation using the Ideogram V3 Balanced model via Replicate. Supports text-to-image generation, inpainting, style transfer with 60+ presets, custom resolutions, and reproducible outputs with local image storage.
2
-
Why this server?
Provides real-time latency ranking of Replicate's free coding LLM models (dev quota). Enables AI agents to select the fastest available model from Replicate's offerings.
MCP server that pings 130+ free coding LLM models across 17 providers in real-time, ranks them by latency, and helps AI agents pick the fastest available model.
21
43 PyPI
MIT
Why this server?
Provides image generation capabilities using Replicate's API, supporting models like FLUX Schnell, FLUX 1.1 Pro, SDXL, and Ideogram.
