mcparmory-replicate 1.0.0

Run AI models, create deployments, and manage predictions via cloud API

Replicate MCP Server

Base URL: https://api.replicate.com/v1

Category	AI & Machine Learning
Tools	37
Auth	Bearer Token

API Info

• Terms of Service: https://replicate.com/terms

---

Install

Quick Start (recommended)

BEARER_TOKEN=YOUR_BEARER_TOKEN \
uvx mcparmory-replicate

With pip

pip install mcparmory-replicate
BEARER_TOKEN=YOUR_BEARER_TOKEN \
mcparmory-replicate

MCP Client Configuration

Add to your MCP client config (e.g. Claude Desktop, Cursor, Codex):

{
  "mcpServers": {
    "replicate": {
      "command": "uvx",
      "args": ["mcparmory-replicate"],
      "env": {
        "BEARER_TOKEN": "YOUR_BEARER_TOKEN"
      }
    }
  }
}

---

Credentials

Set the following environment variables (via MCP client env config, shell export, or .env file):

• BEARER_TOKEN — Bearer token Do not commit credentials to version control.

---

Run Locally

First, configure your credentials in .env (see Credentials above).

pip install -r requirements.txt
python server.py

Connect MCP Client

Edit .mcp.json and replace <SERVER_DIR> with the absolute path to this directory, then add to your MCP client configuration.

Example (if server is at /home/user/mcp-servers/replicate):

{
  "mcpServers": {
    "replicate": {
      "command": "python",
      "args": ["/home/user/mcp-servers/replicate/server.py"]
    }
  }
}

---

Docker

Pre-built image (recommended)

docker run -p 8000:8000 \
  -e BEARER_TOKEN=YOUR_BEARER_TOKEN \
  ghcr.io/mcparmory/replicate:latest

Build from source

First, configure your credentials in .env (see Credentials above).

docker build -t replicate .
docker run -p 8000:8000 --env-file .env replicate

Before running, make sure ports 8000 are free.### MCP client config (Docker)

For Docker, use SSE transport in your MCP client config:

{
  "mcpServers": {
    "replicate": {
      "type": "sse",
      "url": "http://localhost:8000/sse"
    }
  }
}

---

Files

• .env - Credentials and server configuration
• .mcp.json - MCP client config template
• Dockerfile - Container build
• LICENSE - MIT license for this generated code
• requirements.txt - Python dependencies
• README.md - This file
• server.py - MCP server entry point
• _auth.py - Authentication handlers
• _models.py - Request/response models
• _validators.py - Input validation

Note: Files starting with . are hidden by default on macOS/Linux. Use ls -a in terminal or enable "Show hidden files" in your file manager to see .env and .mcp.json.

---

_{Generated by MCP Blacksmith · Quickstart docs · Report a bug}