How to Use the Harness MCP in Google ADK

Q: How do I feed Harness audit logs into Google ADK for analysis?

You use getauditlogs to fetch the raw event history from the MCP server. Google ADK can then pipe this Harness data directly into Vertex AI or BigQuery for pattern analysis.

Q: Where does my Harness connector and pipeline data go when using this MCP server?

Data fetched via listconnectors and listpipelines stays within your secure Google Cloud VPC. The MCP server runs in an isolated sandbox, ensuring zero Harness data leakage to public models used by Google ADK.

Run and monitor Harness deployments inside Google ADK using Gemini's long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harness MCP to Google ADK

Create your Vinkius account to connect Harness 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 Harness with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze long-context Harness execution logs in Google ADK

Detailed step outputs flow directly into your active pipelines via `get_execution_status` over the active MCP link. Because Google ADK runs on Gemini, the agent can ingest massive multi-stage Harness logs using its million-token context window. This allows the Google ADK agent to pinpoint the exact line where a Harness build failed. By matching these logs with Harness pipeline definitions from `get_pipeline`, the Google ADK agent suggests immediate fixes. It reads the entire Harness YAML configuration and execution history in one pass. This eliminates the trial-and-error cycle of debugging complex Harness failures within Google ADK.

Correlate GCP infrastructure with Harness environments

Mapping your physical Google Cloud targets to logical pipelines is straightforward with the `list_environments` MCP tool. The Google ADK agent cross-references your active GKE clusters with your logical Harness targets. This ensures your Google ADK workloads deploy to the correct regional clusters. Using `list_connectors`, the Google ADK agent verifies that your Docker and Git integrations are active. If a Harness registry connector is broken, the Google ADK agent flags it before initiating a build. This prevents orphan container builds on Google Cloud.

Track deployment compliance across enterprise projects

A complete history of platform changes feeds directly into your enterprise agent through `get_audit_logs`. The Google ADK agent can feed these Harness logs into BigQuery to analyze deployment frequency and failure rates. This turns raw Harness events into structured operational metrics inside Google ADK. The Google ADK agent uses `list_projects` to scan your entire Harness organization for non-compliant configurations. It flags Harness projects that lack active audit trails or have misconfigured pipelines. This automated scanning keeps your enterprise Harness deployments aligned with Google Cloud security policies.

Setup guide

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

You use `get_audit_logs` to fetch the raw event history from the MCP server. Google ADK can then pipe this Harness data directly into Vertex AI or BigQuery for pattern analysis.

Yes, Gemini's long context in Google ADK easily processes the large YAML files returned by `get_pipeline`. The Google ADK agent can refactor Harness stages or identify syntax errors instantly.

The MCP server handles the Harness API token authentication externally. Google ADK needs only the connection URL, keeping your Harness deployment credentials isolated from the LLM.

Yes, your Google ADK agent can listen for Pub/Sub events and then call `execute_pipeline` to start a Harness build. It checks the status using `get_execution_status` until completion.

Data fetched via `list_connectors` and `list_pipelines` stays within your secure Google Cloud VPC. The MCP server runs in an isolated sandbox, ensuring zero Harness data leakage to public models used by Google ADK.

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