Retrieve available model collections from Replicate to identify AI models for image generation and inference tasks.
MIT
297,705 tools. Last updated 2026-07-14 08:25
"replicate" matching MCP tools:
- List all static imports of a file to reveal its dependencies. Uses a pre-built import index for fast fuzzy path matching.MIT
- Run up to 50 Replicate predictions in parallel without blocking. Receive a job ID instantly and poll for progress and results.MIT
- List pre-designed complex tasks such as replicating a website or running an SEO audit. Expand a recipe by ID to obtain a ready-to-run prompt with tools and estimated cost.MIT
- Find all files that import a given file, enabling impact analysis before changing a module. Uses a pre-built reverse-import index for fast results.MIT
- Upload a file to Replicate storage by absolute local path or base64 data and receive a temporary URL (valid ~24h) to use as model input.MIT
Matching MCP Servers
- Flicense-qualityDmaintenanceAn MCP server that enables AI assistants to search, discover, and run any model on Replicate.Last updated
- AlicenseAqualityAmaintenanceUniversal MCP server for the full Replicate catalog: image, video, audio, music, speech (TTS+STT), LLMs, vision, upscaling, segmentation, embeddings, voice cloning, 3D, and lipsync. 36 tools and 63 curated models, with async batch + DAG pipeline orchestration and auto-download of outputs.Last updated4361402MIT
Matching MCP Connectors
Run AI models, create deployments, and manage predictions via cloud API
AI LLM with Gemini, MiniMax, Replicate, OpenRouter. Vision, search, code review. USDC on Base.
- Rank curated AI models by speed, cost, quality, or balanced priority. Get top 5 recommendations with cost estimates and reasoning to pick the right model for your task.MIT
- Create instrumental music, full songs with lyrics, or ambient audio from a text description using various generation models.MIT
- Run any model from the Replicate catalog by its owner/name identifier. Supports all categories including embeddings, segmentation, depth estimation, and more.MIT
- Check the status of an async batch prediction job. Get overall status (running, completed, partial) and optional per-item results to monitor progress.MIT
- Generate images from text prompts using Replicate's image models such as Flux Schnell. Customize aspect ratio, model, and number of outputs; results include URLs and optional local downloads.MIT
- Run large language models from Replicate for text generation, Q&A, code writing, summarization, translation, and more. Tune output with customizable model, temperature, system prompt, and generation limits.MIT
- Retrieve the current status and download outputs of a Replicate prediction using its prediction ID, typically after a previous call timed out.MIT
- Run a directed acyclic graph (DAG) of Replicate predictions as a background job. Chain steps with template references for concurrent execution and automatic dependency resolution.MIT
- Poll the status of a running pipeline to check progress and see whether each step completed, failed, or is still pending.MIT
- Synthesize speech using a cloned voice from a short reference audio sample. Provide a URL to the voice sample and the text to speak.MIT
- Search the Replicate model catalog by free-text query to find models for tasks like image upscaling, voice cloning, or code generation. Get up to 25 results with names and descriptions.MIT
- Cancel an in-progress prediction to stop long-running jobs, such as video generation or LLM tasks, that are no longer needed.MIT
- Discover new popular Replicate models missing from the curated registry. Get categorized suggestions with run counts to decide which models to add.MIT
- Kick off a fine-tuning run on a trainable base model with your dataset and hyperparameters. Returns a training ID for status polling.MIT