How to Use the CircleCI MCP in Google ADK

Q: Can Gemini analyze CircleCI job failures using Google ADK tools?

Yes. The agent can use getjobdetails to retrieve the failure logs. Thanks to Gemini's large context window, the agent can read the entire log to diagnose complex build issues.

Q: How do I restrict which CircleCI tools are exposed to my Google ADK agent?

Use the optional toolnames filter when initializing your McpToolset. This lets you limit the agent to read-only actions like listpipelineworkflows while blocking write operations like triggerccipipeline.

Run CircleCI build checks and trigger workflows using Gemini long-context reasoning with 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 CircleCI MCP to Google ADK

Create your Vinkius account to connect CircleCI 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 CircleCI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Correlate BigQuery data with CircleCI pipeline history

This MCP Server lets your Google ADK agent query `list_cci_pipelines` to pull recent run histories directly into your enterprise pipeline. Since the ADK integrates with Google Cloud, you can feed these pipeline statuses into BigQuery to analyze build success rates over time. Your agent can use `get_workflow_details` to fetch metadata for failed runs and cross-reference them with deployment logs stored in Cloud Logging. This gives you a clear picture of how code changes affect your production infrastructure.

Analyze long build logs using Gemini reasoning

Gemini models excel at processing massive contexts, which is perfect when you pull extensive log data using `get_job_details`. The Google ADK agent can ingest the entire job output to find compiler warnings or dependency conflicts that human developers might miss. By combining the `list_workflow_jobs` tool with Gemini's million-token context window, the agent can review every job in a complex workflow at once. This avoids the need to truncate logs or make multiple API calls to understand a failure.

Manage CircleCI workflows with Google ADK integration

Your agent can run `list_cci_contexts` to audit which shared environment variables are configured in your organization. This helps security teams verify that production keys are not exposed to development pipelines. You initialize the toolset using McpToolset with your HTTP server parameters. The Google ADK agent then exposes these tools alongside your custom Vertex AI tools, keeping all your automation inside your Google Cloud VPC.

Setup guide

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

Initialize the toolset using McpToolset with the Vinkius HTTP URL. Pass this toolset into your LlmAgent constructor, and your Gemini-powered agent will immediately be able to run tools like list_cci_pipelines.

Yes. The agent can use get_job_details to retrieve the failure logs. Thanks to Gemini's large context window, the agent can read the entire log to diagnose complex build issues.

Use the optional tool_names filter when initializing your McpToolset. This lets you limit the agent to read-only actions like list_pipeline_workflows while blocking write operations like trigger_cci_pipeline.

Yes. While Vinkius hosts the MCP Server over HTTP, the Google ADK handles the connection natively. This ensures your agent can query get_my_cci_profile and other tools without extra bridge code.

All requests pass through an isolated V8 sandbox that is destroyed immediately after execution. Your build logs and workflow details are processed in memory and never cached, ensuring your proprietary code and configurations remain private.

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