How to Use the Camunda (BPMN Engine) MCP in Google ADK

Q: How do I register the Camunda (BPMN Engine) MCP Server inside Google ADK?

You instantiate McpToolset with your Vinkius HTTP endpoint URL passed to the server parameters. Add this toolset to your LlmAgent constructor inside the tools array to make all 25 process automation tools instantly available to Gemini.

Q: Does the Camunda (BPMN Engine) integration with Google ADK support multi-tenant setups?

Yes, the server includes searchtenants which lets your Google ADK agent query and manage processes across isolated client partitions. You pass the tenant identifier dynamically through your agent's system instructions to maintain strict isolation.

Drive complex Camunda enterprise workflows with Google ADK, leveraging Gemini's long context to analyze entire process histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Camunda (BPMN Engine) MCP to Google ADK

Create your Vinkius account to connect Camunda (BPMN Engine) 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 Camunda (BPMN Engine) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed full BPMN XML contexts to Google ADK

This MCP Server connects your enterprise process engine to Google ADK, allowing your agent to pull entire process structures using `get_process_definition_xml`. Because Gemini models support massive context windows, your agent reads the entire XML file and reasons about complex routing paths instantly. You expose these tools using the `McpToolset` class. The agent queries definitions with `search_process_definitions` and correlates workflow structures with your existing enterprise data warehouses.

Query and resolve cluster incidents in real time

This MCP Server exposes cluster status and active failures to Google ADK through tools like `get_topology` and `search_incidents`. Your agent monitors partition health, identifies bottlenecks, and inspects failing jobs with `search_jobs`. If a partition goes down, the agent correlates the infrastructure state with active processes. It uses `get_process_instance` to find affected workflows and logs the diagnostic report straight to your cloud storage.

Execute high-volume background jobs

This MCP Server lets Google ADK act as a high-throughput external worker by polling for tasks using `activate_jobs` and completing them with `complete_job`. The agent processes data payloads, runs models in Vertex AI, and updates the engine state. You can restrict the agent's scope using the `tool_names` filter in your Python setup. This ensures the model only runs specific actions like job completion while blocking administrative tools.

Setup guide

Set up Camunda (BPMN Engine) 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 Camunda (BPMN Engine) 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="Camunda (BPMN Engine)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Camunda (BPMN Engine) 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 Camunda. 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 Camunda (BPMN Engine) 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 Camunda (BPMN Engine) MCP in Google ADK

You instantiate `McpToolset` with your Vinkius HTTP endpoint URL passed to the server parameters. Add this toolset to your `LlmAgent` constructor inside the tools array to make all 25 process automation tools instantly available to Gemini.

Yes, you can write an agent that queries historical logs in BigQuery and uses `get_variable` or `search_variables` to compare active process states. This allows Gemini to make intelligent routing decisions based on past execution patterns.

Yes, the server includes `search_tenants` which lets your Google ADK agent query and manage processes across isolated client partitions. You pass the tenant identifier dynamically through your agent's system instructions to maintain strict isolation.

You can connect using either Stdio or HTTP transports depending on your hosting environment. For cloud run deployments, the streamable HTTP transport is recommended as it handles connection pooling automatically.

All process definition XMLs, user task assignments, and credentials run inside an ephemeral V8 sandbox on Vinkius. Your Google Cloud environment communicates with the server via a single secure token, ensuring no raw credentials or process schemas are exposed to the public internet or stored on external servers.

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