How to Use the GitGuardian MCP in Pydantic AI

Q: How do I handle GitGuardian API quotas within Pydantic AI?

You can call getquotas at the start of your agent workflow. The returned data is parsed into a type-safe object, allowing your agent to halt execution if your scanning budget is depleted.

Q: How does this setup protect the privacy of my deployed honeytokens?

Honeytoken data generated via createhoneytoken is sent directly to GitGuardian's secure registry. The Vinkius platform acts as a zero-trust proxy, meaning your decoy credentials are never logged or stored in the intermediary server.

Secure your Pydantic AI workflows with type-safe GitGuardian tools that validate security data at runtime.

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 Pydantic AI

Create your Vinkius account to connect GitGuardian to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate scanned code blocks with strict type safety.

This MCP Server provides the `scan_content` tool to analyze raw text blocks and find embedded secrets before they get committed. By using Pydantic AI, your python agent validates the scan output against strict schemas, ensuring that any detected leak contains valid metadata before triggering a security alert. If the scan returns unexpected formatting, the agent fails immediately rather than processing corrupt data. This prevents silent failures when running `scan_and_create_incidents` in your continuous integration pipelines.

Deploy honeytokens using this GitGuardian MCP Server.

The `create_honeytoken` tool generates realistic decoy keys to detect unauthorized access in your environments. Your Pydantic AI agent can programmatically provision these decoys and map their metadata directly to typed Python models. When monitoring your environments, the agent calls `list_honeytoken_events` to check for breach signals. Because every event is validated against a Pydantic model, your downstream alerting systems receive clean, structured data every time.

Triage security incidents with zero type errors.

The `list_secret_incidents` tool retrieves active alerts from your GitGuardian workspace for systematic review. Your Pydantic AI agent parses this list, ensuring fields like incident IDs and severity levels conform exactly to your expected types. The agent can then safely invoke `assign_secret_incident` to route the issue to the correct team member. If an incident requires remediation, the agent calls `resolve_secret_incident` only after confirming all required resolution fields are present and valid.

Setup guide

Set up GitGuardian MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gitguardian-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to GitGuardian tools.",
)

result = await agent.run("List recent GitGuardian transactions")
print(result.output)

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 Pydantic AI

You instantiate the MCP Toolset with the HTTP transport URL from Vinkius. Pass this toolset to your agent constructor to give your model access to all 49 tools, including `scan_content`.

Pydantic AI validates all incoming tool responses at runtime. If a tool like `get_secret_incident` returns a field that violates your schema, the agent raises a validation error, preventing silent failures.

Yes, this MCP Server is model-agnostic. You can pair this server with local models or commercial APIs to run tools like `create_honeytoken` and `list_secret_incidents` safely.

You can call `get_quotas` at the start of your agent workflow. The returned data is parsed into a type-safe object, allowing your agent to halt execution if your scanning budget is depleted.

Honeytoken data generated via `create_honeytoken` is sent directly to GitGuardian's secure registry. The Vinkius platform acts as a zero-trust proxy, meaning your decoy credentials are never logged or stored in the intermediary server.

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