Replicate MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Replicate MCP or direct API to run models, manage jobs, fetch results, and monitor AI pipelines through natural language.
Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Replicate Logo
Gradient Top
Gradient Middle
Gradient Bottom
divider

Try Replicate now

Enter a prompt below to test the integration in our Tool Router playground. You'll be redirected to sign in and try it live.

Supported Tools

Tools
Get Account InformationTool to get authenticated account information.
Cancel PredictionTool to cancel a prediction that is still running.
Get model collectionTool to get a specific collection of models by its slug.
List model collectionsTool to list all collections of models.
Create ModelTool to create a new Replicate model with specified owner, name, visibility, and hardware.
Create PredictionTool to create a prediction for a Replicate Deployment.
Create DeploymentTool to create a new deployment with specified model, version, hardware, and scaling parameters.
Delete DeploymentTool to delete a deployment from your account.
Get Deployment DetailsTool to get deployment details by owner and name.
List deploymentsTool to list all deployments associated with the account.
Create FileTool to create or upload a file to Replicate.
Delete FileTool to delete a file by its ID.
Get File DetailsTool to get details of a file by its ID.
List FilesTool to retrieve a paginated list of uploaded files.
Get PredictionTool to get the status and output of a prediction by its ID.
List Available HardwareTool to list available hardware SKUs for models and deployments.
List model examplesTool to list example predictions for a specific model.
Get Model DetailsTool to get details of a specific model by owner and name.
List Public ModelsTool to list public models with pagination and sorting.
Create Model PredictionTool to create a prediction using an official Replicate model.
Get Model READMETool to get the README content for a model in Markdown format.
Get Model VersionTool to get a specific version of a model.
List Model VersionsTool to list all versions of a specific model.
Create PredictionTool to create a prediction to run a model by version ID.
List All PredictionsTool to list all predictions for the authenticated user or organization with pagination.
Search Models and CollectionsTool to search for models, collections, and docs using text queries (beta).
Cancel TrainingTool to cancel an ongoing training operation in Replicate.
Create Training JobTool to create a training job for a specific model version.
List Training JobsTool to list all training jobs for the authenticated user or organization with pagination.
Update Model MetadataTool to update metadata for a model including description, URLs, and README.
Get Webhook Signing SecretTool to get the signing secret for the default webhook.
Python
TypeScript

Install Composio

python
pip install composio claude-agent-sdk
Install the Composio SDK and Claude Agent SDK

Create Tool Router Session

python
from composio import Composio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions

composio = Composio(api_key='your-composio-api-key')
session = composio.create(user_id='your-user-id')
url = session.mcp.url
Initialize the Composio client and create a Tool Router session

Connect to AI Agent

python
import asyncio

options = ClaudeAgentOptions(
    permission_mode='bypassPermissions',
    mcp_servers={
        'tool_router': {
            'type': 'http',
            'url': url,
            'headers': {
                'x-api-key': 'your-composio-api-key'
            }
        }
    },
    system_prompt='You are a helpful assistant with access to Replicate tools.',
    max_turns=10
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query('Run stable-diffusion to generate a cat image')
        async for message in client.receive_response():
            if hasattr(message, 'content'):
                for block in message.content:
                    if hasattr(block, 'text'):
                        print(block.text)

asyncio.run(main())
Use the MCP server with your AI agent

Why Use Composio?

AI Native Replicate Integration

  • Supports both Replicate MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for running models, tracking jobs, and retrieving predictions

Managed Auth

  • Securely store and manage API keys for Replicate
  • Central dashboard for managing and revoking credentials
  • Scoped, per-user access without sharing secrets in code

Agent Optimized Design

  • Tools tuned for high reliability and clear error reporting
  • Automatic logging of all model runs and fetches per user and agent

Enterprise Grade Security

  • RBAC support to control which agents can run which models
  • Least privilege access for sensitive AI model endpoints
  • Comprehensive audit logs for compliance and oversight

Frequently Asked Questions

Do I need my own developer credentials to use Replicate with Composio?

Yes, Replicate requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.