Replicate MCP Server for Claude Code 12 tools — connect in under 2 minutes
Claude Code is Anthropic's agentic CLI for terminal-first development. Add Replicate as an MCP server in one command and Claude Code will discover every tool at runtime. ideal for automation pipelines, CI/CD integration, and headless workflows via Vinkius.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
Vinkius Desktop App
The modern way to manage MCP Servers — no config files, no terminal commands. Install Replicate and 2,500+ MCP Servers from a single visual interface.
# Your Vinkius token. get it at cloud.vinkius.com
claude mcp add replicate --transport http "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Replicate MCP Server
Connect your conversational assistant directly to the Replicate ecosystem. This integration grants your AI the ability to interact programmatically with a vast library of open-source machine learning models without running them on your local hardware. From orchestrating complex image generations to spinning up specialized language models, you can command AI workflows directly from your chat.
Claude Code registers Replicate as an MCP server in a single terminal command. Once connected, Claude Code discovers all 12 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where Replicate data drives decisions without human intervention.
What you can do
- Execute Predictions — Command the assistant to execute specific model versions on your behalf (
create_prediction) by supplying a payload of variables. Monitor long-running processes by retrieving outputs and execution status reliably (get_prediction) or cancel them at will (cancel_prediction). - Discover Models — Instruct the AI to intelligently scan the Replicate platform for models matching a specific use case using
search_models. You can also explore trending and categorized models by leveraging thelist_collectionsaction. - Analyze Model Metadata — Whenever you discover a new model, query its precise owner and name (
get_model) to extract the exact schema and parameter requirements necessary for a successful execution. You can also view a log of your own executed tasks (list_predictions).
The Replicate MCP Server exposes 12 tools through the Vinkius. Connect it to Claude Code in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Replicate to Claude Code via MCP
Follow these steps to integrate the Replicate MCP Server with Claude Code.
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
Add the MCP Server
Run the command above in your terminal
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
Start using Replicate
Ask Claude: "Using Replicate, show me...". 12 tools are ready
Why Use Claude Code with the Replicate MCP Server
Claude Code provides unique advantages when paired with Replicate through the Model Context Protocol.
Single-command setup: `claude mcp add` registers the server instantly. no config files to edit or applications to restart
Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks
Claude Code runs headlessly, enabling unattended batch processing using Replicate tools in cron jobs or deployment scripts
Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features
Replicate + Claude Code Use Cases
Practical scenarios where Claude Code combined with the Replicate MCP Server delivers measurable value.
CI/CD integration: embed Replicate tool calls in your deployment pipeline to validate configurations or fetch secrets before shipping
Headless batch processing: schedule Claude Code to query Replicate nightly and generate reports without human intervention
Shell scripting: pipe Replicate outputs into other CLI tools for data transformation, filtering, and aggregation
Infrastructure monitoring: run Claude Code in a cron job to query Replicate status endpoints and alert on anomalies
Replicate MCP Tools for Claude Code (12)
These 12 tools become available when you connect Replicate to Claude Code via MCP:
cancel_prediction
Cancels a prediction that is currently running
create_prediction
g., image generation, LLMs). Provide the model version ID and inputs as a JSON object. Starts a new model prediction on Replicate
get_account
Retrieves the authenticated Replicate account details
get_collection
Provide the collection slug (e.g., "text-to-image"). Retrieves a specific collection of models by its slug
get_model
Retrieves details for a specific model
get_prediction
). Retrieves the status and output of a prediction
list_collections
g., "Image-to-Text", "Audio Generation"). Lists curated collections of models
list_deployments
Lists your active model deployments on Replicate
list_hardware
Lists available GPU hardware options for running models
list_models
Lists public models available on Replicate
list_predictions
Lists recent predictions made by the user
search_models
Searches for public models on Replicate
Example Prompts for Replicate in Claude Code
Ready-to-use prompts you can give your Claude Code agent to start working with Replicate immediately.
"List my recent predictions."
"Query Replicate to search for 'TTS' models."
"Cancel the prediction that has the ID `p_abc123`."
Troubleshooting Replicate MCP Server with Claude Code
Common issues when connecting Replicate to Claude Code through the Vinkius, and how to resolve them.
Command not found: claude
npm install -g @anthropic-ai/claude-codeConnection timeout
Replicate + Claude Code FAQ
Common questions about integrating Replicate MCP Server with Claude Code.
How do I add an MCP server to Claude Code?
claude mcp add --transport http "" in your terminal. Claude Code registers the server and discovers all tools immediately.Can Claude Code run MCP tools in headless mode?
How do I list all connected MCP servers?
claude mcp in your terminal to see all registered servers and their status, or type /mcp inside an active Claude Code session.Connect Replicate with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Replicate to Claude Code
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.