How to Use the Pylon MCP in Google ADK

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

Install the package using pip install google-adk. Create an McpToolset pointing to your Vinkius HTTP URL, then pass that toolset into the tools parameter of your LlmAgent.

Q: Can I limit which Pylon tools are exposed to Google ADK?

Yes, you can use the optional toolnames filter when initializing your McpToolset. This prevents the agent from seeing or executing write operations like replytoissue or createissue.

Q: How does Gemini's long context benefit Pylon ticket resolution?

Gemini can ingest hundreds of messages fetched via getissuemessages at once. This allows the Google ADK to understand the entire history of a complex B2B dispute before drafting a reply.

Feed 1M+ tokens of B2B support history directly to Gemini models using Google ADK and the Pylon MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pylon MCP to Google ADK

Create your Vinkius account to connect Pylon to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pylon with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Analyze ticket trends with the Pylon MCP Server

This MCP Server provides `list_issues` to let your Gemini agents pull massive batches of customer tickets in a single call. Because the Google ADK handles long-context windows, your agent can ingest months of support history to spot recurring bugs. You pass the Pylon toolset to your Google ADK `LlmAgent` to let it correlate ticket data with your infrastructure logs. The agent maps active issues against your BigQuery datasets to find out if a cloud outage is causing the spike in customer complaints.

Sync customer accounts with Vertex AI data pipelines

Your agents run `get_account` and `list_accounts` to pull company metadata directly into your Google Cloud workflows. This lets you combine CRM data with predictive models running on Vertex AI to flag accounts at risk of churning. After identifying high-risk accounts, the agent uses `update_issue` to escalate their active tickets automatically. You configure this connection using `McpToolset` with your HTTP server parameters to keep the data flowing.

Draft replies using enterprise knowledge bases

Gemini agents use `list_knowledge_bases` and `list_articles` to search your internal help docs. The long-context model reads entire articles to extract precise troubleshooting steps for complex B2B setups. The agent then uses `reply_to_issue` to send the resolution directly to the customer. If you want to limit the agent to writing tasks, pass a `tool_names` filter to the ADK to restrict access to read-only tools.

Setup guide

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

Install the package using `pip install google-adk`. Create an `McpToolset` pointing to your Vinkius HTTP URL, then pass that toolset into the `tools` parameter of your `LlmAgent`.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset`. This prevents the agent from seeing or executing write operations like `reply_to_issue` or `create_issue`.

It does. For production setups on Google Cloud, we recommend using the Streamable HTTP transport via Vinkius to keep your server running independently of your agent process.

Gemini can ingest hundreds of messages fetched via `get_issue_messages` at once. This allows the Google ADK to understand the entire history of a complex B2B dispute before drafting a reply.

Your B2B support tickets and account records are transmitted over encrypted HTTPS channels directly to your VPC. Google ADK processes these payloads in memory without writing any Pylon account details or ticket bodies to persistent storage in the Vinkius secure MCP sandbox.

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