How to Use the NLP Cloud MCP in Google ADK

Q: How do I configure the NLP Cloud MCP Server with the Google ADK?

Install google-adk via pip. Initialize an McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass that toolset to your LlmAgent so Gemini can access the endpoints.

Q: Can Google ADK restrict which NLP Cloud tools the agent sees?

Yes. You use the optional toolnames filter when setting up the toolset. This prevents the agent from calling the translation endpoint if it only needs to run text classification.

Feed BigQuery data into NLP Cloud through the Google ADK for massive-scale text processing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NLP Cloud MCP to Google ADK

Create your Vinkius account to connect NLP Cloud 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 NLP Cloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect the NLP Cloud MCP Server

The `classify_text` and `analyze_sentiment` tools run natively inside your Google ADK pipelines. You define an `McpToolset` with your Vinkius endpoint and pass it to your `LlmAgent`. The Gemini model immediately knows how to categorize your text strings and score their emotional tone. This matters because enterprise data lives in Google Cloud. You can pull a million rows of customer feedback from BigQuery and let Gemini run the analysis. The model's massive context window means it can read huge chunks of data before deciding exactly which text needs classification.

Process media files with Gemini

Call `perform_asr` to pull transcripts from audio and video files stored in your GCP buckets. The agent grabs the media, formats the required JSON payload, and hits the MCP endpoint. You get raw text back without leaving your Vertex AI environment. Gemini's massive token limit pairs perfectly with long transcripts. Once the audio becomes text, the agent can immediately run `extract_entities` to pull out names, dates, and locations. You filter the exposed tools using `tool_names` in your setup so the agent only sees the endpoints it actually needs.

Multilingual summarization pipelines

Your agent uses `translate_text` and `summarize_text` to process foreign documents at scale. It reads the source material, translates it into English, and condenses it down to the core facts. You handle the connection using HTTP transports in your Python code. Google ADK makes this fast. You skip writing custom integration code for every API endpoint. The SDK maps the tool schemas directly to Gemini's native function calling, turning your cloud infrastructure into an automated translation and summarization engine.

Setup guide

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

Install `google-adk` via pip. Initialize an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass that toolset to your `LlmAgent` so Gemini can access the endpoints.

Yes. You use the optional `tool_names` filter when setting up the toolset. This prevents the agent from calling the translation endpoint if it only needs to run text classification.

Gemini's million-token context window handles the reading, while the connected tools handle the specific operations. The agent can ingest a massive BigQuery export and selectively trigger the summarization tool on specific paragraphs.

It integrates directly. Your agent runs within your existing Google Cloud infrastructure, pulling data from your storage buckets and passing it to the external tools as needed.

You only need a single endpoint token to authenticate. When Gemini sends video files or text strings to the Vinkius environment, they hit an isolated sandbox. The system processes the audio or text and destroys the container immediately, ensuring zero persistent storage of your Google Cloud data.

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