How to Use the GitGuardian MCP in Google ADK

Q: Can my Google ADK agent filter which GitGuardian incidents it triages?

Yes. You can use the listsecretincidents tool with specific query parameters to only return critical severity leaks, allowing your agent to prioritize high-risk keys.

Q: How does GitGuardian verify that honeytokens are deployed correctly via Google ADK?

The agent can call listhoneytokensources to check exactly where a decoy credential has been placed. This guarantees that your automated deployment pipeline successfully injected the token into your targeted Google Cloud assets.

Q: How are my API keys protected when scanned by GitGuardian via Google ADK?

All credential payloads sent via scancontent are processed in memory using secure HTTPS connections. GitGuardian analyzes the signatures to verify the leak, while the Vinkius sandbox ensures no sensitive strings are logged or persisted.

Secure your Google ADK enterprise pipelines by connecting GitGuardian tools to detect secrets and manage incidents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitGuardian MCP to Google ADK

Create your Vinkius account to connect GitGuardian 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 GitGuardian with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scan massive code repositories using Google ADK.

This MCP Server exposes the `scan_content` tool to process raw text blocks and detect exposed API keys, database passwords, and private keys. Google ADK lets your Gemini agent ingest massive codebases from BigQuery, run them through this scanning tool, and pinpoint leaks across millions of lines of code. When the model identifies a risk, it uses `scan_and_create_incidents` to log the vulnerability directly into your GitGuardian workspace. This keeps your enterprise data pipelines clean without requiring manual code reviews.

Deploy decoy traps across Google Cloud infrastructure.

The `create_honeytoken_with_context` tool places realistic decoy credentials inside your cloud configuration files to catch intruders. Your Google ADK agent can automatically run this tool during deployment steps, injecting unique honeytokens into Vertex AI pipelines or Cloud Storage buckets. If an external actor accesses these decoys, the agent monitors the activity using `list_honeytoken_events`. It can immediately execute `revoke_honeytoken` to neutralize the threat before any production data is accessed.

Manage security incidents with GitGuardian MCP Server.

The `list_secret_incidents` tool retrieves all active credential leaks detected across your enterprise repositories. Your Google ADK agent pulls this list, correlates the incidents with deployment logs, and updates their status in real time. The agent can run `resolve_secret_incident` once a developer rotates the leaked key, or `ignore_secret_incident` if it confirms a false positive. You can export this entire triage history directly to BigQuery for long-term compliance reporting.

Setup guide

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

You initialize the MCP Toolset with the HTTP endpoint provided by Vinkius. Pass this toolset directly to your agent constructor so Gemini can access tools like `scan_content` and `create_honeytoken`.

Yes. You can use the `list_secret_incidents` tool with specific query parameters to only return critical severity leaks, allowing your agent to prioritize high-risk keys.

The agent can call `list_honeytoken_sources` to check exactly where a decoy credential has been placed. This guarantees that your automated deployment pipeline successfully injected the token into your targeted Google Cloud assets.

Yes. This MCP Server allows Gemini to call multiple tools simultaneously, such as running `scan_content` across different files in parallel, accelerating your pre-deployment security checks.

All credential payloads sent via `scan_content` are processed in memory using secure HTTPS connections. GitGuardian analyzes the signatures to verify the leak, while the Vinkius sandbox ensures no sensitive strings are logged or persisted.

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