Bring Machine Learning
to Cursor
Create your Vinkius account to connect Replicate to Cursor and start using all 12 AI tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code. No hosting, no server setup — just connect and start using.
Compatible with every major AI agent and IDE
What is the 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.
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).
How it works
- Install the Replicate platform extension module in your MCP.
- Provide your personal
Replicate API Token, extracted from your Replicate Account Settings panel. Deposit it securely into the configuration variables below. - Prompt your assistant organically: "Search for a high-quality video generation model, evaluate its parameter schema, and start generating a clip using the prompt 'a cat walking on Mars'."
Who is this for?
- AI Developers & Researchers — Explore and test novel open-source algorithms by generating quick predictions without modifying Python notebook code.
- Content Creators — Execute specialized image, audio, or video generation tasks by directly delegating workflows to your conversational assistant.
- Builders — Mix and match the output of various specialized models intelligently using natural language instructions.
Built-in capabilities (12)
Cancels a prediction that is currently running
g., image generation, LLMs). Provide the model version ID and inputs as a JSON object. Starts a new model prediction on Replicate
Retrieves the authenticated Replicate account details
Provide the collection slug (e.g., "text-to-image"). Retrieves a specific collection of models by its slug
Retrieves details for a specific model
). Retrieves the status and output of a prediction
g., "Image-to-Text", "Audio Generation"). Lists curated collections of models
Lists your active model deployments on Replicate
Lists available GPU hardware options for running models
Lists public models available on Replicate
Lists recent predictions made by the user
Searches for public models on Replicate
Why Cursor?
Cursor's Agent mode turns Replicate into an in-editor superpower. Ask Cursor to generate code using live data from Replicate and it fetches, processes, and writes. all in a single agentic loop. 12 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Replicate in Cursor
Why run Replicate with Vinkius?
The Replicate connection runs on our fully managed, secure cloud infrastructure. We handle the hosting, maintenance, and security so you don't have to deal with servers or code. All 12 tools are ready to work instantly without any complex setup.
You stay in complete control of your data. Your AI only accesses the information you approve, keeping your sensitive passwords and private details completely safe. Plus, with automatic optimizations, your AI works faster and more efficiently.

* Every connection is hosted and maintained by Vinkius. We handle the security, updates, and infrastructure so you don't have to write code or manage servers. See our infrastructure
Over 4,000 integrations ready for AI agents
Explore a vast library of pre-built integrations, optimized and ready to deploy.
Connect securely in under 30 seconds
Generate tokens to authenticate and link external services in a single step.
Complete visibility into every agent action
Audit live requests, latency, success rates, and active security compliance policies.
Optimize spending and track token ROI
Analyze real-time token consumption and cost metrics detailed by connection.




Explore our live AI Agents Analytics dashboard to see it all working
This dashboard is included when you connect Replicate using Vinkius. You will never be left in the dark about what your AI agents are doing with your tools.
Replicate and 4,000+ other AI tools. No hosting, no code, ready to use.
Professionals who connect Replicate to Cursor through Vinkius don't need to write code, manage servers, or worry about security. Everything is pre-configured, secure, and runs automatically in the background.
Raw MCP | Vinkius | |
|---|---|---|
| Ready-to-use MCPs | Find and configure each manually | 4,000+ MCPs ready to use |
| Connection Setup | Manual coding & server setup | 1-click instant connection |
| Server Hosting | You host it yourself (needs 24/7 uptime) | 100% hosted & managed by Vinkius |
| Security & Privacy | Stored in plaintext config files | Bank-grade encrypted vault |
| Activity Visibility | Blind execution (no logs or tracking) | Live dashboard with real-time logs |
| Cost Control | Runaway AI token spend risk | Automatic budget limits |
| Revoking Access | Must delete files or code to stop | 1-click disconnect button |
How Vinkius secures
Replicate for Cursor
Every request between Cursor and Replicate is protected by our secure gateway. We automatically keep your sensitive data private, prevent unauthorized access, and let you disconnect instantly at any time.
Frequently asked questions
Can the agent pass a JSON payload directly into a Replicate model?
Yes. You can utilize the create_prediction action and attach the payload parameter filled out with any required input schema (e.g., specific prompt, num_inference_steps). Since models change inputs constantly, you should always ask your assistant to fetch the schema details first via get_model to verify keys.
Does the prediction command return results instantly?
No, Replicate's API operates asynchronously. The initial command gives your assistant an ID. You must then ask your AI companion to query the get_prediction tool periodically using that generated ID until it displays the completed status along with the generated web URLs or generated strings.
Can the AI browse trending or curated model collections?
Yes. Use the list_collections tool to browse curated groups of models organized by category — such as image generation, text-to-speech, or video. Each collection includes a slug and description so you can quickly identify the right set of models for your use case.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Payfunnels
12 toolsBuild payment funnels and checkout experiences that maximize conversions with upsells, order bumps, and subscription options.

GoCardless
12 toolsCollect recurring payments directly from bank accounts with automated direct debit that reduces failed payment rates.

Poplar
11 toolsAutomate programmatic direct mail via Poplar — trigger mailers, standardize addresses, and manage audiences directly from any AI agent.

LEAP Legal
10 toolsManage legal matters, cards (contacts), and documents via the LEAP API.
