How to Use the GitGuardian MCP in OpenAI Agents SDK

Q: How does GitGuardian handle rate limiting when queried by OpenAI Agents SDK?

The agent checks your current usage limits using getquotas before triggering bulk scans. If you hit GitGuardian API limits, the SDK handles the retries based on your configured backoff policy.

Q: How does this setup handle the privacy of my scanned source code?

The scancontent tool transmits code snippets over an encrypted HTTPS connection to GitGuardian for signature matching. No code is stored on the Vinkius platform, and the ephemeral sandbox discards all payload data immediately after the scan completes.

Protect your codebase from leaked credentials by deploying GitGuardian tools directly into your OpenAI Agents SDK pipelines.

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 OpenAI Agents SDK

Create your Vinkius account to connect GitGuardian to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run automated pre-commit scans inside OpenAI Agents SDK.

The `scan_content` tool scans raw text and code snippets for active credentials before your agent commits them to a repository. Your OpenAI Agents SDK pipeline intercepts outbound code blocks, routes them through this scan, and blocks execution if it finds a high-entropy string or known API key. If a leak occurs, the agent switches to the `scan_and_create_incidents` tool to log the event instantly in your dashboard. By using built-in SDK guardrails, the agent halts the pipeline and alerts the security team, preventing the secret from ever reaching your main branch.

Deploy honeytokens using this GitGuardian MCP Server.

The `create_honeytoken` tool generates decoy credentials that trigger alerts the moment an attacker tries to use them. Your OpenAI Agents SDK system can coordinate specialized security agents to deploy these decoys across test environments, staging databases, or documentation files automatically. When an agent detects a potential breach, it calls `list_honeytoken_events` to check if any decoys were tripped. The agent then passes this telemetry to a response agent that uses `revoke_honeytoken` to kill the compromised decoy immediately.

Triage security alerts with safety guardrails.

The `list_secret_incidents` tool fetches active credential leaks from your workspace for agent evaluation. Using the OpenAI Agents SDK, your agent parses these incidents, checks their severity, and updates their status without human intervention. You enforce strict safety constraints so the agent can only execute `assign_secret_incident` or `ignore_secret_incident` after verifying the incident metadata. By adding this MCP Server to your environment, every decision is fully logged in your OpenAI tracing dashboard, giving you a clear audit trail of how your agent resolved each leak.

Setup guide

Set up GitGuardian MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all GitGuardian tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GitGuardian tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GitGuardian tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="GitGuardian Agent",
            instructions="You have access to GitGuardian tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You install the SDK and pass the server URL to the streamable HTTP constructor. The SDK auto-discovers all 49 tools, including `scan_content` and `create_honeytoken`, making them instantly available to your agent.

Yes. You can apply runtime guardrails within the OpenAI Agents SDK to intercept tool calls. If an agent tries to run `resolve_secret_incident` but lacks authorization, your wrapper blocks the execution.

The agent checks your current usage limits using `get_quotas` before triggering bulk scans. If you hit GitGuardian API limits, the SDK handles the retries based on your configured backoff policy.

Yes, you can register multiple MCP tools inside your agent constructor. This allows your OpenAI Agents SDK configuration to query security data and write updates to your issue tracker in a single run.

The `scan_content` tool transmits code snippets over an encrypted HTTPS connection to GitGuardian for signature matching. No code is stored on the Vinkius platform, and the ephemeral sandbox discards all payload data immediately after the scan 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