How to Use the Cody AI MCP in Google ADK

Q: How do I connect the Cody AI MCP Server to my Google ADK agent?

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent constructor inside the tools array to expose the Cody capabilities.

Q: Can I limit which Cody AI tools my Google ADK agent can access?

Yes, you can pass a toolnames filter list to your toolset configuration. This lets you restrict the agent to read-only actions like listdocuments while blocking modification tools.

Q: How does Google ADK utilize Cody AI bots for customer support?

Google ADK queries the bots via sendmessage to retrieve answers from your trained knowledge base. It uses its long-context window to analyze the bot's response alongside your enterprise BigQuery logs.

Connect Cody AI knowledge bases to your Google ADK pipelines for enterprise-grade Gemini reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cody AI MCP to Google ADK

Create your Vinkius account to connect Cody AI 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 Cody AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise knowledge mapping for Google ADK

Give your Gemini agents access to your support files by linking this MCP Server to your Google Cloud setup. The agent uses `list_folders` and `list_documents` to find where your enterprise manuals are stored. This setup lets you combine BigQuery data with unstructured files. Your agent can query Cody bots using `send_message` to get context, then write those insights back to your cloud data warehouse.

Automated ingestion of web documentation

Keep your enterprise bots updated without manual uploads. Your Gemini-powered agent can identify outdated documentation in your knowledge base and use `import_webpage` to pull down the newest web pages. The agent then monitors the sync progress with `get_document_status`. Once the status shows as complete, your agent can immediately query the updated bot for accurate customer responses.

Context-rich conversation management

Long-context Gemini models need complete histories to work their magic. Use `list_messages` to retrieve entire historical threads via the MCP interface and feed them directly into your agent's reasoning window. When a customer returns, your agent uses `list_conversations` to find past sessions. It can then resume the exact context via `create_conversation`, ensuring your enterprise support feels continuous.

Setup guide

Set up Cody AI 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 Cody AI 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="Cody AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cody AI 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 Cody AI. 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 Cody AI 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 Cody AI MCP in Google ADK

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into your `LlmAgent` constructor inside the tools array to expose the Cody capabilities.

Yes, you can pass a `tool_names` filter list to your toolset configuration. This lets you restrict the agent to read-only actions like `list_documents` while blocking modification tools.

Yes, the toolset supports both transport options. For cloud-hosted environments, the HTTP transport is recommended to connect securely to your managed Vinkius endpoint.

Google ADK queries the bots via `send_message` to retrieve answers from your trained knowledge base. It uses its long-context window to analyze the bot's response alongside your enterprise BigQuery logs.

Your proprietary web URLs and crawled text are transmitted over encrypted TLS directly to Cody. Vinkius processes these imports in a secure sandbox, ensuring no raw HTML or document content is exposed to external networks.

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