run_replicate_model
Runs any model hosted on Replicate by its owner/name[:version] reference. Use this as an escape hatch when none of the curated tools fit. Call getmodelschema first if you don't know the input shape.
How to use it
Project documentation lists run_replicate_model for the Replicate Flux MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Replicate Flux MCP
npx -y replicate-flux-mcpOther tools in Replicate Flux MCP (8)
Generates an image based on a text prompt using the configured image model (allowlist only).
Generates multiple variants of the same image from a single prompt using the configured image model (allowlist only).
Generates multiple images based on an array of prompts using the configured image model (allowlist only).
Generates SVG/vector output based on a text prompt using the configured SVG model (allowlist only).
Fetches the OpenAPI input schema and description for a Replicate model so you can pass the right parameters to runreplicatemodel.
Gets detailed information about a specific prediction.
Retrieves a list of your recent predictions from Replicate.
Runs a whitelisted Replicate model with a raw input payload (useful for video or restoration models).