# Replicate — MCP server on mcp.ai
> Connect your Replicate account and use 31 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Replicate allows users to run AI models via a cloud API without managing infrastructure.

By: mcp.ai · official
Page: https://mcp.ai/replicate

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_replicate?ms=1787293440000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/replicate/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/replicate/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/replicate/skill.md
Postman collection (v2.1): https://mcp.ai/replicate/postman.json

## Tools
- replicate_account_get() — Tool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
- replicate_cancel_prediction(prediction_id: string) — Tool to cancel a prediction that is still running. Use when you need to stop an in-progress prediction to free up resources or halt execution.
- replicate_collections_get(collection_slug: string) — Tool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
- replicate_collections_list(cursor?: string) — Tool to list all collections of models. Use when you need to retrieve available model collections. Collections are curated groupings of related models. Response includes only collection metadata (name
- replicate_create_model(name: string, owner: string, hardware: string, paper_url?: string, github_url?: string, visibility: string, description?: string, license_url?: string, cover_image_url?: string) — Tool to create a new Replicate model with specified owner, name, visibility, and hardware. Use when you need to create a destination model before launching LoRA/fine-tune training.
- replicate_create_prediction(input: object, webhook?: string, wait_for?: integer, deployment_name: string, deployment_owner: string, webhook_events_filter?: string[]) — Tool to create a prediction for a Replicate Deployment. IMPORTANT: This action ONLY works with Replicate Deployments (persistent instances you create and manage), NOT public models. Deployments are cr
- replicate_deployments_create(name: string, model: string, version: string, hardware: string, max_instances: integer, min_instances: integer) — Tool to create a new deployment with specified model, version, hardware, and scaling parameters. Use when you need to deploy a model for production use with auto-scaling.
- replicate_deployments_delete(deployment_name: string, deployment_owner: string) — Tool to delete a deployment from your account. Use when you need to remove a deployment. Deployments must be offline and unused for at least 15 minutes before deletion.
- replicate_deployments_get(deployment_name: string, deployment_owner: string) — Tool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings.
- replicate_deployments_list(cursor?: string) — Tool to list all deployments associated with the account. Use when you need to retrieve deployment configurations and their latest releases.
- replicate_files_create(content: object, metadata?: object, content_type?: string) — Tool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata.
- replicate_files_delete(file_id: string) — Tool to delete a file by its ID. Use when you need to remove a file from storage. Returns 204 No Content on success.
- replicate_files_get(file_id: string) — Tool to get details of a file by its ID. Use when you need to inspect uploaded file information before further operations. Returned URLs may be short-lived; download or persist needed files promptly a
- replicate_files_list(cursor?: string) — Tool to retrieve a paginated list of uploaded files. Use to view all files created by the authenticated user or organization. Files are sorted with most recent first. Pagination is cursor-based: follo
- replicate_get_prediction(prediction_id: string) — Tool to get the status and output of a prediction by its ID. Use when you need to check on a running prediction or retrieve the results of a completed prediction.
- replicate_hardware_list() — Tool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform.
- replicate_models_examples_list(cursor?: string, model_name: string, model_owner: string) — Tool to list example predictions for a specific model. Use when you want to retrieve author-provided illustrative examples after identifying the model. Returned examples are minimal working payloads; 
- replicate_models_get(model_name: string, model_owner: string) — Tool to get details of a specific model by owner and name. Consult the returned input schema before constructing any prediction request — each model defines its own required/optional fields (e.g., `pr
- replicate_models_list(cursor?: string, sort_by?: string, sort_direction?: string) — Tool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date.
- replicate_models_predictions_create(input: object, webhook?: string, wait_for?: integer, model_name: string, model_owner: string, cancel_after?: string, webhook_events_filter?: string[]) — Tool to create a prediction using an official Replicate model. Use when you need to run inference with a specific model using its owner and name. Supports synchronous waiting (up to 60 seconds) and we
- replicate_models_readme_get(model_name: string, model_owner: string) — Tool to get the README content for a model in Markdown format. Consult alongside REPLICATE_MODELS_EXAMPLES_LIST before calling REPLICATE_CREATE_PREDICTION — Replicate enforces strict JSON schemas on m
- replicate_models_versions_get(model_name: string, version_id: string, model_owner: string) — Tool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata.
- replicate_models_versions_list(cursor?: string, model_name: string, model_owner: string) — Tool to list all versions of a specific model. Use when you need to see all available versions of a model, sorted by newest first.
- replicate_predictions_create(input: object, stream?: boolean, version: string, webhook?: string, wait_for?: integer, cancel_after?: string, webhook_events_filter?: string[]) — Tool to create a prediction to run a model by version ID. Use when you have a specific model version identifier and need to run inference with provided inputs. Supports synchronous waiting and webhook
- replicate_predictions_list(cursor?: string, created_after?: string, created_before?: string) — Tool to list all predictions for the authenticated user or organization with pagination. Use when you need to retrieve prediction history or filter predictions by creation date.
- replicate_search(limit?: integer, query: string) — Tool to search for models, collections, and docs using text queries (beta). Use when you need to find relevant models or collections based on keywords or descriptions.
- replicate_trainings_cancel(training_id: string) — Tool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
- replicate_trainings_create(name: string, input: object, owner: string, webhook?: string, version_id: string, destination: string, webhook_events_filter?: string[]) — Tool to create a training job for a specific model version. Use when you need to fine-tune a model with custom training data. Supports webhook notifications for training status updates.
- replicate_trainings_list(cursor?: string) — Tool to list all training jobs for the authenticated user or organization with pagination. Use when you need to retrieve training history or check the status of training jobs.
- replicate_update_models(readme?: string, paper_url?: string, github_url?: string, model_name: string, description?: string, license_url?: string, model_owner: string, weights_url?: string) — Tool to update metadata for a model including description, URLs, and README. Use when you need to modify a model's visibility, documentation, or associated links.
- replicate_webhooks_secret_get() — Tool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity.

## Example prompts
- "What can I do in Replicate?"
- "Show me a summary of my Replicate account"

## Links
Docs: https://mcp.ai/docs/mcps/replicate
Website: https://mcp.ai/mcps/replicate