How to Use the Convai MCP in Google ADK

Q: How do I configure the Convai MCP Server within Google ADK?

Install google-adk and define your server parameters using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset directly into your LlmAgent tools array to expose the tools.

Q: Can Google ADK agents manage live audio connections to Convai?

Yes. Your agent can call connectlive to initiate a WebRTC connection. This allows your Gemini models to coordinate real-time audio streams for voice-based virtual characters.

Q: How does Convai work with Gemini's long-context window in Google ADK?

Gemini can analyze massive documents and then use uploadknowledgebank to push synthesized knowledge directly to your Convai character. This keeps your character's memory sharp without hitting API limits.

Q: Can I limit which tools are exposed to my agent?

Yes, you can use the optional toolnames filter when setting up your MCP server toolset. This lets you restrict your agent to specific operations, like only allowing character lookups via getcharacter while blocking deletion tools.

Connect Gemini's massive context window to Convai characters using the Google ADK to build enterprise-grade game worlds.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convai MCP to Google ADK

Create your Vinkius account to connect Convai to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Convai with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed BigQuery Data directly to Convai Characters

The Convai MCP Server allows your Google ADK agent to sync enterprise data sources directly into your virtual character's brain. By executing `upload_knowledge_bank` or `update_knowledge_bank`, your pipeline pulls structured data from BigQuery and pushes it straight to Convai. This setup lets you build customer-facing virtual assistants that actually know your product catalog inside out. Instead of manually updating files, your Gemini-powered agent handles the entire lifecycle programmatically.

Build Narrative Trees inside Google ADK

This MCP Server gives your Gemini models direct control over complex story states and NPC behaviors. Your agent can run `create_narrative_section` and `list_narrative_triggers` to construct deep, branching dialogue systems based on user input. Gemini's million-token context window excels at keeping track of massive narrative webs. By combining Google Cloud's reasoning power with these tools, your agent can maintain consistent storylines across hours of conversation without losing the thread.

Manage Voice and Language Settings at Scale

The integration provides tools like `list_voices` and `list_languages` to customize how your virtual agents sound to global audiences. Your Google ADK system can query available voice models and dynamically update character profiles using `update_character`. This means you can localize your game or application on the fly. If a user switches their preferred language, your agent detects the change and updates the character's voice settings in seconds.

Setup guide

Set up Convai MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Convai tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Convai_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Convai tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Convai. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Convai now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Convai MCP in Google ADK

Install `google-adk` and define your server parameters using `StreamableHttpServerParameters` with your Vinkius URL. Pass this toolset directly into your `LlmAgent` tools array to expose the tools.

Yes. Your agent can call `connect_live` to initiate a WebRTC connection. This allows your Gemini models to coordinate real-time audio streams for voice-based virtual characters.

Gemini can analyze massive documents and then use `upload_knowledge_bank` to push synthesized knowledge directly to your Convai character. This keeps your character's memory sharp without hitting API limits.

Yes, you can use the optional `tool_names` filter when setting up your MCP server toolset. This lets you restrict your agent to specific operations, like only allowing character lookups via `get_character` while blocking deletion tools.

All character backstory data is transmitted securely through Vinkius's zero-trust infrastructure. Your data runs in isolated sandboxes, ensuring your proprietary game lore never leaks to third parties.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript