How to Use the Apache APISIX MCP in Google ADK

Q: How do I initialize the Apache APISIX tools inside a Google ADK agent?

You use the McpToolset class pointing to your Vinkius HTTP URL. Pass this toolset directly to your LlmAgent to expose all 50 gateway tools to Gemini via MCP.

Q: Can Gemini analyze Apache APISIX health check data in BigQuery?

Yes, your agent can pull raw logs from BigQuery and use getcontrolhealthcheck to compare database records against live gateway status.

Q: Does the Google ADK support limiting the exposed Apache APISIX tools?

You can use the optional toolnames filter during initialization to restrict access. This prevents Gemini from running high-risk commands like deleteglobalrule.

Q: How does the agent handle Protocol Buffers for gRPC routing?

The agent uses putproto to upload .proto files directly to the gateway. This allows APISIX to handle gRPC transcoding and routing automatically.

Q: Where are my APISIX routing rules and upstream IP addresses processed?

All routing data and upstream IPs fetched by dumpcontrolupstreams stay within your Google Cloud boundary. Vinkius processes these MCP requests through a secure sandbox that never stores your configuration state.

Connect Gemini's 1M+ token context to your Apache APISIX admin API using Google ADK to analyze and configure routes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apache APISIX MCP to Google ADK

Create your Vinkius account to connect Apache APISIX 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 Apache APISIX with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Audits via Google ADK MCP Server

Gemini's massive context window lets you feed thousands of lines of gateway telemetry directly to your agent. The Google ADK agent calls `dump_control_routes` and `dump_control_services` to ingest your entire APISIX configuration in one go. Once ingested, the agent cross-references these configurations with active BigQuery traffic logs. It identifies unused routes and recommends cleanup actions to keep your gateway lean.

Zero-Downtime L4 and L7 Routing Updates

Managing complex protocol buffers and stream routes becomes simple with Gemini's reasoning. Your agent invokes `put_proto` and `put_stream_route` to deploy new gRPC or TCP services. If a deployment fails, the agent queries `get_control_resource_healthcheck` to isolate the broken upstream node. It automatically rolls back the change using `put_route` to keep your APIs online.

Global Policy and SSL Automation

Security compliance requires constant updates to global rules and SSL certificates. The MCP Server lets your agent monitor expiring certificates and call `put_ssl` to apply renewed credentials before they lapse. It also enforces rate-limiting across all endpoints by applying `put_global_rule`. This keeps your backend services safe from sudden traffic spikes or DDoS attempts.

Setup guide

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

You use the `McpToolset` class pointing to your Vinkius HTTP URL. Pass this toolset directly to your `LlmAgent` to expose all 50 gateway tools to Gemini via MCP.

Yes, your agent can pull raw logs from BigQuery and use `get_control_healthcheck` to compare database records against live gateway status.

You can use the optional tool_names filter during initialization to restrict access. This prevents Gemini from running high-risk commands like `delete_global_rule`.

The agent uses `put_proto` to upload `.proto` files directly to the gateway. This allows APISIX to handle gRPC transcoding and routing automatically.

All routing data and upstream IPs fetched by `dump_control_upstreams` stay within your Google Cloud boundary. Vinkius processes these MCP requests through a secure sandbox that never stores your configuration state.

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