How to Use the 42Crunch MCP in Google ADK

Q: Can Google ADK filter which 42Crunch MCP tools the agent sees?

Yes, you can use the optional toolnames filter. This restricts the agent to specific read-only actions like getauditreport if you want to prevent accidental deletions.

Q: How does the agent know which collection to target?

It calls listcollections to grab the internal IDs. The agent then uses those IDs as parameters for subsequent actions like importing new specifications.

Give your Gemini agents direct access to 42Crunch security testing through 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 42Crunch MCP to Google ADK

Create your Vinkius account to connect 42Crunch 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 42Crunch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

42Crunch MCP Server Integration

The `import_api` tool lets your Gemini agent pull OpenAPI specs directly from your Google Cloud storage buckets and push them into the testing platform. It handles the entire ingestion phase without manual uploads. Gemini's massive context window means you can dump the full output of `get_scan_report` straight into the prompt. The agent reads the entire dynamic conformance scan, cross-referencing it with internal BigQuery logs to find the exact source of a vulnerability.

Trigger Static Security Checks

Firing off `trigger_audit` tells the platform to evaluate a newly updated specification. The agent waits for completion and immediately pulls the findings using `get_audit_report`. Enterprise teams can wire this into Vertex AI pipelines. Every time a developer commits a new endpoint, the agent automatically grades it and blocks the merge if the security score drops below your required threshold.

Audit Workspace Navigation

Agents navigate your testing workspace using `list_collections` to find specific project folders. Once inside, `list_apis` returns every definition along with its current security grade. Getting granular details requires the `get_api` and `get_collection` tools. Your agent pulls the exact metadata needed to decide if an old, failing endpoint should be removed via `delete_api`.

Setup guide

Set up 42Crunch 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 42Crunch 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="42Crunch_agent",
    model="gemini-2.0-flash",
    instruction="You have access to 42Crunch 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 42Crunch. 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 42Crunch 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 42Crunch MCP in Google ADK

Run pip install google-adk to get the framework. Create an McpToolset using StreamableHttpServerParameters with your Vinkius endpoint, then pass it to the LlmAgent tools array.

Yes, you can use the optional tool_names filter. This restricts the agent to specific read-only actions like get_audit_report if you want to prevent accidental deletions.

The integration is native to the Gemini ecosystem. Any LlmAgent you build can call these security tools and combine the results with your existing GCP infrastructure.

It calls list_collections to grab the internal IDs. The agent then uses those IDs as parameters for subsequent actions like importing new specifications.

Everything operates within a stateless V8 Isolate Sandbox. The raw dynamic conformance logs and vulnerability data transmit securely through the managed tunnel, tearing down immediately after the request completes.

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