Replicate MCP Server

Replicate MCP Server

A universal, cross-platform MCP server that gives any MCP client — Claude Desktop, the claude.ai web app (Connectors), Cursor, Cline / Continue in VS Code, or your own application — native access to the full Replicate catalog: image generation, video, music, speech, upscaling, segmentation, LLMs, voice cloning, 3D, lipsync — anything Replicate hosts.

It speaks both transports: stdio (the standard for local desktop/editor integrations) and HTTP/SSE (for remote/web clients and your own services).

Once connected to your MCP client, you can simply ask:

_"Generate a cinematic shot of a lighthouse in a storm, 21:9"_

_"Write a 30-second synthwave track"_

_"Make a 5-second video of a paper airplane flying through a city"_

_"Read this paragraph in a British male voice"_

_"Upscale this image 4x"_

…and the assistant calls the right Replicate model, waits for the result, and (on local/stdio setups) downloads the output to your machine.

---

Install

Fastest — one-click via [Smithery](https://smithery.ai/server/sena-labs/replicate-mcp-server): open the server page and copy the Install snippet for your client (Claude, Cursor, VS Code, Cline, Windsurf, …). It wires the server in and prompts for your Replicate token. _(Routes through Smithery's hosted gateway — easiest, zero local setup.)_

Token-private — npm + stdio (your Replicate token never leaves your machine):

npx -y replicate-mcp-server

…or drop it into any MCP client's config (full walkthrough under Installation).

Claude Desktop one-file install: download the latest .mcpb from Releases and drag it onto Claude Desktop.

Already running (bring your own token): https://replicate-mcp.sena-labs.dev/mcp — HTTP/SSE, multi-tenant; pass your token in the x-replicate-api-token header.

Once connected, try the example prompts below.

---

Try it

Once your client is connected, ask in plain language — the assistant picks the right tool, waits for the result, and downloads the output locally:

_"Generate a cinematic shot of a lighthouse in a storm, 21:9"_

_"Which is the cheapest model for a 5-second video? Then use it."_ — recommend → generate

_"Make 4 logo variations of a fox, flat vector style"_ — batch (concurrent)

_"Transcribe this audio, summarise it, then read the summary aloud"_ — DAG pipeline

_"Upscale this image 4×"_ · _"Write a 30-second synthwave track"_ · _"Read this in a British male voice"_

_"Kick off a Flux LoRA fine-tune on my dataset and tell me when it's done"_ — training

Discovery tools (replicate_recommend_model, replicate_search_models, replicate_estimate_cost) and the 5 built-in workflow prompts help it chain multi-step jobs without you naming models.

---

What's inside

36 tools and 66 curated models, designed to be both ergonomic for common cases and fully open-ended for everything else. Every generate/run tool waits for completion and auto-downloads the outputs to your machine — you ask once and get back local files, not a job id to babysit:

Curated generation tools

Voice, 3D, and avatar tools

Orchestration tools

Fine-tuning (trainings)

Deployments

Prediction management + cost

Generic / discovery tools

Outputs:

• Image / video / audio: downloaded to ~/Downloads/replicate-mcp/ / / (configurable). Local paths and original Replicate URLs are both returned. For images, the response also includes an inline base64 preview (sized to stay under Claude Desktop's 1 MB tool-result limit; larger images fall back to the URL embed) plus three embed snippets ( -wrapped iframe viewer with Save button, responsive , or markdown image) so the chat client can render the result inline at full size.
• Text (LLM, vision, classifier): the model's reply is surfaced in text_output and printed at the top of the tool response so Claude can read it directly.

Editing an image you have on hand

The editing tools (replicate_upscale_image, replicate_inpaint, replicate_remove_background, replicate_vision, image-to-video, lipsync, 3D-from-image) all take a URL. To turn a file into a URL, use replicate_upload_file:

• You have a local path (Claude Desktop): replicate_upload_file({ file_path: "C:/Users/you/photo.jpg" }) → URL → pass to the editing tool. If an image is dragged/pasted into the chat, save it to disk first — the server cannot read chat attachments directly, and Claude Desktop cannot reproduce a large image's exact bytes as a tool argument.
• You have the bytes in memory (claude.ai web with a code container): read the uploaded file in the container, base64-encode it, then replicate_upload_file({ base64_data: "data:image/png;base64,..." }) → URL → editing tool. base64_data accepts a bare base64 string or a full data: ;base64,... URI.
• You already have a URL: pass it straight to the editing tool — no upload needed.

---

Why this over the official Replicate MCP?

Replicate ships its own official MCP (replicate-mcp on npm, hosted at mcp.replicate.com). It's a great, free, always-up-to-date 1:1 bridge to the REST API — Stainless-generated from Replicate's OpenAPI spec, ~37 generic tools that mirror each endpoint (account, collections, deployments, files, hardware, models, predictions, trainings, webhooks), plus a --tools=dynamic mode and a Deno "Code Mode" sandbox.

This server is built for a different job. The official MCP is a thin, generic API bridge: to make an image you call create_predictions with a raw model id and raw input JSON, and the LLM has to look up each model's input schema itself; it returns starting and does not wait or download (you opt into Prefer: wait, capped at 60s, then poll manually). This server is a batteries-included creative studio: task-oriented tools with sane defaults, a curated model registry, built-in orchestration, and cost awareness — every generate/run tool waits for completion and auto-downloads the outputs locally.

| Fine-tuning + deployments | Yes (generic REST) | Yes — create/get/list/cancel_training + list/get/run_deployment (run waits + down