Skip to main content

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

Project description

Replicate MCP Server

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

Category AI & Machine Learning
Tools 37
Auth Bearer Token

API Info


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.


MCP Blacksmith
Generated by MCP Blacksmith · Quickstart docs · Report a bug

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcparmory_replicate-1.0.1-py3-none-any.whl (48.2 kB view details)

Uploaded Python 3

File details

Details for the file mcparmory_replicate-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcparmory_replicate-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a1ec13c86d08e16801e591444c2d893e90dea71d715bedae8ffddc2ab0cb37ed
MD5 dff35fb1124214388565c815cfcceb78
BLAKE2b-256 937e36bcbf5b8bcb6de633369d748ef603969b5049eb2ece61b55d17b6c6269a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page