How to Use the Archbee MCP in Google ADK

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

Install google-adk and initialize McpToolset using your Vinkius HTTP server parameters. Pass this toolset into your LlmAgent configuration. This exposes all 19 tools to your Gemini models instantly.

Q: Can my Google ADK agent sync OpenAPI specs to Archbee?

Yes. Your Gemini agent can call syncopenapi to update documentation directly from your API build pipelines. It can also use infoopenapi to verify that the schema parsed correctly before publishing.

Q: How does the Google ADK handle MCP tool execution limits with Archbee?

You can use the optional toolnames filter in the McpToolset constructor. This lets you restrict the agent to specific tools like searchdocs and getdoc, keeping its focus tight and preventing unauthorized edits.

Let Gemini agents analyze BigQuery data and write technical docs in Archbee using this MCP Server and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Archbee MCP to Google ADK

Create your Vinkius account to connect Archbee 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 Archbee with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive doc spaces with Google ADK

Feed entire documentation libraries into Gemini's million-token context window by using `search_docs` to find relevant information across your organization. Once found, pull the exact content with `get_doc`. Once the analysis is complete, the Google ADK agent can structure new guides using `import_content`. This lets you combine your enterprise Google Cloud data with your existing Archbee documentation base.

Build portals using this MCP Server

Automate your developer portal setup by running `create_space` to generate a new portal directly from Vertex AI pipelines. Then, use `get_display_rules` to apply your brand's access permissions. If you need to replicate a successful documentation layout, the Google ADK agent executes `clone_space`. This MCP Server ensures all your API portals follow the same structure and design rules without manual setup.

Manage documentation assets programmatically

Upload and manage technical assets directly from your Google Cloud Storage buckets using `upload_file` within your Google ADK pipeline. This makes them immediately available for your technical docs. For major cleanups or migrations, the Google ADK agent can call `delete_space_group` to remove retired product documentation. This keeps your external developer portal clean and focused on active services.

Setup guide

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

Install `google-adk` and initialize `McpToolset` using your Vinkius HTTP server parameters. Pass this toolset into your `LlmAgent` configuration. This exposes all 19 tools to your Gemini models instantly.

Yes. Your Gemini agent can call `sync_openapi` to update documentation directly from your API build pipelines. It can also use `info_openapi` to verify that the schema parsed correctly before publishing.

You can use the optional `tool_names` filter in the `McpToolset` constructor. This lets you restrict the agent to specific tools like `search_docs` and `get_doc`, keeping its focus tight and preventing unauthorized edits.

Yes. Because the agent runs within the Google Cloud ecosystem, it can query BigQuery, format the results, and use `create_update_doc` to write those insights directly into your spaces.

Yes. All tool interactions run through a zero-trust network architecture hosted on Vinkius. Your organization exports from `export_organization` are processed in memory and never written to disk, preventing data leaks.

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