How to Use the Geetest MCP in Google ADK

Q: How do I connect Geetest to Google ADK?

Install the google-adk package. Initialize an McpToolset with StreamableHttpServerParameters pointing to your endpoint, then pass it to your LlmAgent tools list.

Q: Can Google ADK filter which Geetest tools my agent sees?

Yes. You can use the toolnames filter in the McpToolset constructor. This lets you expose validatecaptcha to a public-facing agent while restricting setpolicy to an internal admin agent.

Q: How secure is the Geetest MCP Server data processed by Google ADK?

The tool handles raw captchaoutput hashes and behavioral risk scores. Vinkius wraps this server in an ephemeral zero-trust container, ensuring that sensitive token payloads are never logged to disk during agent execution.

Feed threat intelligence into Gemini. The Geetest MCP integration for Google ADK stops bots and logs attacks directly to your cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geetest MCP to Google ADK

Create your Vinkius account to connect Geetest 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 Geetest with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Score Threat Risk with Google ADK

The `validate_with_risk` tool gives your Gemini agent the behavioral data it needs to block credential stuffing before it hits your database. The agent takes the `lot_number`, `captcha_output`, `pass_token`, and `gen_time` from your frontend, runs the validation, and analyzes the risk score. Enterprise agents need context. Because Gemini handles massive token windows, you can feed the results from `validate_captcha` directly into a broader threat analysis prompt. Your agent decides whether to allow the request or trigger a Vertex AI pipeline for further investigation.

Analyze Geetest MCP Server Metrics

The `get_validation_stats` tool exposes MCP CAPTCHA effectiveness metrics to your Google ADK pipelines. Your agent pulls these attack patterns and can immediately write the findings into BigQuery for long-term fraud analysis. You can also verify your frontend setup using `get_captcha_config`. When a Gemini agent notices a drop in successful human validations, it checks the config to see if someone accidentally pushed a misconfigured environment variable to production.

Automate Bot Management

The `get_blocked_ips` tool lets your agent fetch the list of addresses currently blocked by the CAPTCHA system. You can pipe this list straight into Google Cloud Armor rules to block repeat offenders at the network edge. When an attack escalates, manual intervention is too slow. Your agent can execute `set_policy` to instantly increase CAPTCHA friction. The changes apply immediately, stopping the botnet while your team sleeps.

Setup guide

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

Install the `google-adk` package. Initialize an `McpToolset` with `StreamableHttpServerParameters` pointing to your endpoint, then pass it to your `LlmAgent` tools list.

Yes. You can use the `tool_names` filter in the `McpToolset` constructor. This lets you expose `validate_captcha` to a public-facing agent while restricting `set_policy` to an internal admin agent.

The agent receives a boolean failure state and a risk reason from the tool. You can prompt Gemini to return a specific HTTP 403 response or trigger a custom fallback workflow.

The MCP standard supports both HTTP and Stdio. For Vinkius-hosted endpoints, you will use the Streamable HTTP transport with your provided access token.

The tool handles raw `captcha_output` hashes and behavioral risk scores. Vinkius wraps this server in an ephemeral zero-trust container, ensuring that sensitive token payloads are never logged to disk during agent execution.

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