Log inSubmit server
Replicate logo

Replicate

Run Replicate models, inspect versions, manage predictions, and use deployments through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Replicate

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "replicate": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-replicate"
      ],
      "env": {
        "PLATFORM_REPLICATE_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 16 tools correctly (22d ago).

Overview

Replicate MCP server exposes Replicate's API for discovering public models, starting predictions, polling results, and managing deployments. It supports gateway-based streamable HTTP access through Pipeworx or a standalone local stdio process. Use it when an agent needs to run models such as Flux, Llama, or Whisper and handle asynchronous prediction workflows. Authentication uses a Replicate platform key or a request-level API key.

Use cases

  • Search Replicate's public model catalog
  • Run a model prediction and poll its status
  • Stream LLM-style prediction output over SSE
  • Inspect model versions before selecting a run
  • Execute predictions through a deployment

Key features

  • Public model search and discovery
  • Prediction creation, polling, listing, and cancellation
  • Webhook and SSE streaming options
  • Deployment-based prediction runs
  • Account and hardware queries
  • Hosted gateway and local stdio modes

Tools16

What Replicate lets your agent do. Expand a tool for its parameters.

Verified live~926 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

10/10 checks healthy over the last 44d

What it can do

From the 16 tools this server returned when we ran it.

Makes network requests · 4Read-only tools · 16
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age34 days
Maintainers1

Observed 2026-10-21 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @pipeworx/mcp-replicate (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads6.9kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed16Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Replicate works

What Replicate MCP server does

The Replicate MCP server connects MCP clients to the Replicate API at https://api.replicate.com/v1. It gives agents access to public model discovery, model and version details, collections, predictions, deployments, account information, and available hardware types.

Model tools cover searching and browsing Replicate's catalog. An agent can list public models, retrieve a model, inspect its versions, search by query, and view collections or an individual collection. Prediction tools start runs, retrieve an individual prediction, list recent predictions, and cancel a running job.

The service also supports deployment-based runs. Agents can list deployments, inspect a deployment, and create a prediction through a deployment, which is intended for faster cold starts. The available models and their behavior remain determined by Replicate.

How it works

A prediction request returns before the model necessarily finishes. After calling create_prediction or create_deployment_prediction, the client should poll prediction(id) until the status is succeeded or failed. Alternatively, the request can include a webhook URL and optional webhook event filters so Replicate can notify an external endpoint.

For LLM-style output, callers can set stream=true. The response provides a urls.stream Server-Sent Events endpoint for receiving the stream.

The Replicate MCP server is available in two forms. The hosted endpoint is exposed through the Pipeworx gateway and can be configured as an MCP URL. The standalone package runs locally over stdin and stdout and exposes only the Replicate pack's tools. The hosted pack endpoint also lists shared Pipeworx meta-tools, including routing and discovery tools; its initialize response is the authoritative source for the tools available on a given day.

Setup and configuration

For hosted use, add https://gateway.pipeworx.io/replicate/mcp as the MCP server URL in a compatible client. The full Pipeworx gateway at https://gateway.pipeworx.io/mcp is another option; both URLs reach the same gateway, while the listed direct tools differ.

For local use, configure the client to run npx -y @pipeworx/mcp-replicate. The process communicates through MCP over stdin/stdout and does not require a Pipeworx account or gateway round trip. The package can also be started directly with the same npx command.

Authentication uses PLATFORM_REPLICATE_KEY. The gateway documentation also describes a BYO API key passed as ?_apiKey=….

Tools and capabilities

The Replicate MCP server includes these capability groups:

  • Models: list_models, model, model_versions, model_version, search_models, collections, and collection.
  • Predictions: create_prediction, prediction, list_predictions, and cancel_prediction.
  • Deployments: list_deployments, deployment, and create_deployment_prediction.
  • Account: account and hardware.

The gateway also provides shared Pipeworx tools on the hosted pack endpoint, while the local package does not. Tools can additionally be called over HTTP through gateway routes such as /v1/tools/replicate_list_models.

Limitations and notes

Prediction execution is asynchronous, so an agent must poll or provide a webhook rather than assuming that creation returns final output. Streaming requires handling the returned SSE URL. Hosted pack connections include extra shared tool schemas, which can increase the tool list and context compared with the standalone process. The standalone process does not provide Pipeworx-wide routing through ask_pipeworx.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Replicate

Replicate is an MCP server that connects AI agents to the Replicate API. Its main tools search public models, inspect model versions, create and monitor predictions, cancel runs, use deployments, and query account or hardware details. It supports hosted Pipeworx gateway access and a local stdio package.

Run `npx -y @pipeworx/mcp-replicate` as a local stdio MCP server, or configure an MCP client with the hosted URL `https://gateway.pipeworx.io/replicate/mcp`. The local package does not require a Pipeworx account or gateway round trip.

Yes, Replicate works with Cursor through the hosted MCP URL shown in the setup example. The README also names Claude Desktop and Windsurf as compatible client examples, and the package can run locally over standard MCP stdio.

Poll `prediction(id)` until the status is `succeeded` or `failed`, or provide a webhook URL when creating the prediction. For LLM-style streaming, set `stream=true` and consume the returned `urls.stream` SSE endpoint.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewReplicate AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/replicate?style=directory)](https://allmcps.com/mcp/replicate)
HTML Embed
<a href="https://allmcps.com/mcp/replicate"><img src="https://allmcps.com/api/badge/replicate?style=directory" alt="Replicate on AllMCPs" /></a>