Replicate
sena-labs/replicate-mcp-serverUniversal MCP server — works with any MCP client (Claude Desktop, the claude.ai web app, Cursor, Cline, or your own host). Gives native access to the full Replicate catalog — image, video, music, speech (TTS + STT), LLMs, vision, upscale, inpaint, segment, embeddings, voice cloning, 3D generation, lipsync/avatar, trainings (fine-tune) and deployments, and anything else hosted on replicate.com. 36 tools, 66 curated models. Every generate/run tool waits for completion and auto-downloads outputs. Includes a pre-call cost estimator, prediction history / cancel tools, multi-token round-robin pool, rate-limit awareness, and both stdio and a webhook-friendly HTTP/SSE transport.
Watch this dependency
Get before/after evidence when observed tools, schemas, authentication access, availability or the endpoint changes.
Inspect evidence and set up a watch Share public evidence report
Score: 100/100
Handshake verified by our own probe.
why this score
Tools · 36
Generate one or more images from a text prompt using a Replicate image model. Use this for any "draw / create / generate an image of …" request. By default it uses Flux Schnell (fast, ~2 seconds per …
Generate a video clip from a text prompt (and optionally a starting image). Video generation is slow — typically 1-5 minutes per clip. DISPLAY REQUIREMENT — after this tool returns successfully, incl…
Generate music, ambient audio, or full songs from a text prompt. DISPLAY REQUIREMENT — after this tool returns successfully, include the URL(s) printed in the tool's text content as a markdown link `…
Convert text to natural-sounding speech. DISPLAY REQUIREMENT — after this tool returns successfully, include the URL printed in the tool's text content as a markdown link `[Speech](URL)` in your repl…
Run a large language model hosted on Replicate. Use this for free-form text generation, Q&A, code writing, summarisation, translation — anything where the input is text and the output is text. Args: …
Run a vision-language model to describe, caption, or answer questions about an image. Args: - image (string URL): URL of the image to analyse. - prompt (string, optional): Question or instruction…
Upscale an image to higher resolution. Optional face restoration for photos. DISPLAY REQUIREMENT — after this tool returns successfully, embed the upscaled image inline using one of the three blocks …
Produce a transparent-background version (PNG) of an image. DISPLAY REQUIREMENT — after this tool returns successfully, embed the cut-out image inline using one of the three blocks (iframe / <img> / …
Transcribe an audio or video file to text using Whisper-family models on Replicate. Args: - audio (URL): URL of the audio (or video) to transcribe. - model (default "incredibly-fast-whisper"): Cu…
Fill masked regions of an image based on a text prompt. Works for both inpainting (replace inside) and outpainting (extend canvas) when the mask covers the target area. DISPLAY REQUIREMENT — embed th…
Produce a segmentation mask of an image. Use SAM 2 for point/box-prompt masks (auto-mask everything when no prompt given) or Grounded-SAM for text-prompt masking like "the red car". DISPLAY REQUIREME…
Convert text(s) into numeric embedding vectors. Useful for RAG, semantic search, clustering, similarity scoring. Args: - texts: A single string or an array of strings (max 256). Each text is embedd…
Synthesize speech in a cloned voice. Provide a short reference audio sample (~5-30 s) and the text to speak; the model reproduces the voice characteristics. DISPLAY REQUIREMENT — after this tool retu…
Generate a 3D mesh (GLB/OBJ) from a text prompt or a reference image. 3D generation is slow — typically 1-5 minutes. DISPLAY REQUIREMENT — after this tool returns successfully, include the download U…
Animate a portrait image to speak — either from a text script (model does TTS + lipsync) or from a driving audio file. Produces an MP4 video. DISPLAY REQUIREMENT — after this tool returns successfull…
Generic escape hatch: run ANY model in the Replicate catalog by its "owner/name" identifier. This tool gives Claude access to the entire Replicate model catalog — anything not covered by the curated s…
Search the Replicate catalog by free-text query. Returns up to 25 matching models with names, descriptions, and URLs. Args: - query (string, 1-200 chars): Free-text search. Examples: "image upscale…
Retrieve metadata and the OpenAPI input/output schema for a specific Replicate model. Use this before replicate_run_model to know which fields the model accepts and what they mean. Args: - model (s…
Retrieve the current status and (if available) outputs of a Replicate prediction by its ID. Use this when a previous generate_* or run_model call returned pending=true (timed out before completion). …
Upload a file to Replicate's file storage and get back a URL valid for ~24 hours. Pass the returned URL as a model input (e.g. image for upscale/inpaint/vision, image_url for video, reference_audio_ur…
Rank the curated models in a category by a priority (speed, cost, quality, or balanced) and return recommendations with cost estimates and reasoning. This does NOT run anything — it advises which mode…
Run a directed acyclic graph (DAG) of Replicate predictions as a background job. Returns a pipeline_id immediately. Poll replicate_pipeline_status for per-step progress and results. Independent steps…
Poll the status of a pipeline started with replicate_pipeline_start. Args: - pipeline_id (string): Pipeline ID returned by replicate_pipeline_start. - include_outputs (boolean, default true): Inc…
Run multiple Replicate predictions in parallel as a background job. Returns a job_id immediately — the predictions run in the background. Poll replicate_batch_status for progress and results. Use thi…
Poll the status of an async batch job started with replicate_batch_start. Args: - job_id (string): Job ID returned by replicate_batch_start. - include_results (boolean, default true): Include ful…
Return the most recent predictions on the authenticated Replicate account. Useful to recover a prediction ID, audit recent calls, or check what's still running. Args: - limit (1-100, default 10): H…
Cancel an in-progress prediction by its ID. Useful for long-running async jobs (video, large LLM) when the user no longer needs the result. Args: - prediction_id (string): ID of the prediction to c…
Return an approximate dollar-cost estimate for a planned prediction BEFORE running it. Prices are a hand-curated snapshot — actual billing comes from Replicate. Call this when the user asks "how much …
Search Replicate for popular models NOT yet in the curated registry. Returns suggestions only — does not modify code. Use this to find new models worth adding. Then ask Claude to edit src/models.ts w…
Kick off a fine-tuning (training) run on a trainable base model — e.g. a Flux LoRA trainer — with your dataset and hyperparameters. Returns immediately with a training ID; poll it with replicate_get_t…
Retrieve the current state of a training run: status, the resulting trained model version (once it succeeds), and any error. Args: - training_id: ID returned by replicate_create_training. Returns …
Return the most recent training runs on the authenticated account. Args: - limit (1-100, default 10): How many trainings to return. Returns structuredContent: { count: number, trainings: TrainingS…
Cancel an in-progress training run by its ID. Trainings can run for many minutes and cost real money — cancel when no longer needed. Args: - training_id: ID of the training to cancel. Returns stru…
List the deployments on the authenticated Replicate account. A deployment is a private, autoscaled endpoint pinned to a specific model + hardware. Args: - limit (1-100, default 20): How many deploy…
Get the configuration of one deployment: its current model + version, hardware, and autoscaling min/max instances. Args: - deployment: "owner/name" of the deployment. Returns structuredContent: De…
Run a prediction against a deployment's current release. WAITS for the prediction to finish and (by default) auto-downloads the outputs locally — same UX as the curated generate_* tools. Args: - de…
Resources · 2
Every curated model this server knows, grouped by category, with the Replicate id, a one-line description, and a speed tier. Pass any key (or an 'owner/name[:version]') as a tool's `model` argument.
replicate://models
A summary of this server: categories covered, model count, transports, and the orchestration features (async batch, DAG pipelines, model recommender, cost estimator).
replicate://capabilities
Prompts · 5
Generate an image, video, audio clip, or speech from a plain-language description. Picks the matching replicate_generate_* tool and a sensible default model.
Pick the best Replicate model for a task given a priority (speed, cost, or quality), then run it. Calls replicate_recommend_model and feeds the winner into the right generate tool.
Run the same generation over many inputs concurrently. Uses replicate_batch_start with a list of prompts, then polls replicate_batch_status until done.
Compose a multi-step pipeline that first generates an image, then animates it into a video. Uses replicate_pipeline_start with a two-step DAG and $stepId.field references.
Transcribe an audio/video file with speech-to-text, then summarise the transcript. Uses replicate_transcribe_audio and returns key points.
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"replicate": {
"url": "https://replicate-mcp.sena-labs.dev/mcp",
"transport": "http"
}
}
}