How to Use the BugHerd MCP in Google ADK

Q: Can my Google ADK agent analyze thousands of BugHerd tasks at once?

Yes, by combining the listtasks tool with Gemini's million-token context window, your agent can process your entire BugHerd backlog in a single reasoning loop.

Q: How do I limit which BugHerd tools are exposed to my Google ADK agent?

You can pass an optional toolnames filter when creating your McpToolset. This lets you restrict the agent to read-only tools like gettask if you want to prevent automated updates.

Q: How does this BugHerd MCP Server integration protect sensitive user directories?

The listusers tool only accesses the metadata required to assign tasks. Vinkius runs the BugHerd integration in a sandboxed V8 sandbox, ensuring your user list and project details are never leaked to external parties.

Run enterprise-grade Gemini agents that sync BugHerd feedback with your BigQuery data using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugHerd MCP to Google ADK

Create your Vinkius account to connect BugHerd 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 BugHerd with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context feedback analysis with Google ADK

The `list_tasks` tool pulls all active feedback items from a specific BugHerd project directly into your Gemini context window. Because the Google ADK works with long-context models, you can feed thousands of bug reports into a single run to detect macro trends in user feedback. Your agent can cross-reference these issues with historical crash logs stored in BigQuery. Once the analysis is complete, the agent can use `update_task` to assign priority levels based on actual system performance data.

Automated comment syncing from Vertex AI

The `add_comment` tool allows your Gemini agent to post automated resolutions directly onto BugHerd tasks. By using this tool within the Google ADK, you can build enterprise workflows that monitor internal databases and reply to QA teams when a bug is fixed in production. Before posting, the agent can run `list_comments` to read the entire conversation history. This guarantees that the agent has full context and does not repeat instructions that another engineer already provided.

Enterprise user mapping and task creation

The `list_users` tool helps your Google ADK agent map BugHerd accounts to your internal Google Cloud directory. When a critical bug is detected via your monitoring pipelines, the agent can match the right engineer and run `create_task` to assign it immediately. This setup uses the standard MCP Server transport protocol to handle the execution securely. You can filter the exposed tools in your McpToolset configuration to ensure the agent only performs authorized actions.

Setup guide

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

You use McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset directly to your LlmAgent instance, and your Gemini model will immediately see the BugHerd tools.

Yes, by combining the list_tasks tool with Gemini's million-token context window, your agent can process your entire BugHerd backlog in a single reasoning loop.

You can pass an optional tool_names filter when creating your McpToolset. This lets you restrict the agent to read-only tools like get_task if you want to prevent automated updates.

Yes, this MCP Server can be consumed via either transport method. For cloud-hosted Google ADK deployments, the streamable HTTP endpoint hosted on Vinkius is the recommended approach.

The list_users tool only accesses the metadata required to assign tasks. Vinkius runs the BugHerd integration in a sandboxed V8 sandbox, ensuring your user list and project details are never leaked to external parties.

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