How to Use the SketricGen MCP in Google ADK

Q: How do I manage complex workflows with SketricGen using the Google ADK?

You kick off an entire process by calling runworkflow. The MCP Server executes a series of connected tools and agents. Your agent simply needs to call this function, and the workflow handles the rest.

Q: What kind of history can SketricGen provide when using the Google ADK?

You get full visibility into execution paths using listtraces and gettrace. This detailed logging is critical for debugging. It shows every step, which helps you prove system integrity to your stakeholders.

Q: Can SketricGen help with knowledge retrieval when using the Google ADK?

Yes. You manage context by accessing specific knowledgebases through getknowledgebase. This ensures that any agent's reasoning is backed up by verifiable, corporate data.

Q: How do I check if SketricGen is operational when using the Google ADK?

You verify connectivity immediately by calling checksketricgenstatus. This function confirms that all endpoints are up and ready to accept commands from your agent.

Build enterprise agents on Google Cloud using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SketricGen MCP to Google ADK

Create your Vinkius account to connect SketricGen 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 SketricGen with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Execute Complex Workflows

Trigger multi-step processes by calling `run_workflow`. This tool allows your agent to coordinate several specialized services, passing data through a defined workflow structure. It's designed for large-scale operations where multiple systems must interact. Since you're building enterprise agents on Google Cloud, the MCP Server ensures that all workflows are auditable and repeatable. You get predictable results every time you call `run_workflow`.

Manage Knowledge Context

Keep your agents grounded in company facts by accessing knowledge bases. Use `list_knowledge_bases` to see what's available, and then `get_knowledge_base` to retrieve the content for a specific context. This keeps hallucination risk low. If you need to know how an agent behaves generally, checking `get_agent` provides full details on its capabilities within the MCP Server environment.

Audit All Actions

When troubleshooting, use `list_traces` and `get_trace` to get a complete record of execution. This tells you exactly what happened during a run—which tools fired and with which inputs. You can also check resource consumption using `get_trace_credits`. Need to see the full context? Calling `list_workflows` shows all available operational blueprints, so you know what's possible.

Setup guide

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

You kick off an entire process by calling `run_workflow`. The MCP Server executes a series of connected tools and agents. Your agent simply needs to call this function, and the workflow handles the rest.

You get full visibility into execution paths using `list_traces` and `get_trace`. This detailed logging is critical for debugging. It shows every step, which helps you prove system integrity to your stakeholders.

Yes. You manage context by accessing specific `knowledge_bases` through `get_knowledge_base`. This ensures that any agent's reasoning is backed up by verifiable, corporate data.

You maintain control over conversations. You can list all past chats using `list_conversations`, or explicitly delete a specific record by calling `delete_conversation`.

You verify connectivity immediately by calling `check_sketricgen_status`. This function confirms that all endpoints are up and ready to accept commands from your agent.

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