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.

Replicate MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: Replicate
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Replicate as an MCP tool provider through the Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token — get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="replicate_agent",
    instruction=(
        "You help users interact with Replicate "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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.

Google ADK natively supports Replicate as an MCP tool provider — declare the Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

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 the list_collections action.
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 Google ADK 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 Google ADK via MCP

Follow these steps to integrate the Replicate MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from Replicate via MCP

Why Use Google ADK with the Replicate MCP Server

Google ADK provides unique advantages when paired with Replicate through the Model Context Protocol.

Google ADK natively supports MCP tool servers — declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Replicate

Production-ready features like session management, evaluation, and deployment come built-in — not bolted on

Seamless integration with Google Cloud services means you can combine Replicate tools with BigQuery, Vertex AI, and Cloud Functions

Replicate + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Replicate MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Replicate and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Replicate tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Replicate regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Replicate

Replicate MCP Tools for Google ADK (12)

These 12 tools become available when you connect Replicate to Google ADK 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 Google ADK

Ready-to-use prompts you can give your Google ADK 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 Google ADK

Common issues when connecting Replicate to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Replicate + Google ADK FAQ

Common questions about integrating Replicate MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.