How to Use the Aikido Security MCP in Pydantic AI

Q: What's the setup process for Aikido Security with Pydantic AI?

After installing pydantic-ai-slimmcp, you create an MCPToolset instance with your Vinkius MCP server URL. Then you pass this toolset to your agent's constructor. It’s a clean way to add all the Aikido Security tools at once.

Get type-safe security data from Aikido Security. Your Pydantic AI agent won't fail silently on bad API responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aikido Security MCP to Pydantic AI

Create your Vinkius account to connect Aikido Security 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 Aikido Security with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Reliable Security Reports

When you build security reports, you need the data to be right. With Pydantic AI, every response from the Aikido MCP server is validated against a Pydantic model. If your agent calls `list_open_issues` and the API returns an unexpected field, your code will raise a `ValidationError` immediately. This means no more silent data corruption or hallucinated fields in your reports. Your agent can pull compliance status with `get_iso_compliance` or `get_soc2_compliance`, and you can be certain the data structure matches what your application expects. It's about trusting the data you're acting on.

Audit Your Aikido Config with Pydantic AI

Use a Pydantic AI agent to audit your Aikido setup. It can call `list_teams`, `list_users`, and `list_code_repositories` to give you a structured overview of your organization. The response for each is a validated object, not just a blob of JSON. This is great for writing maintenance scripts. Have an agent check `list_connected_clouds` and `list_webhooks` to make sure your integrations are healthy. If the API ever changes or returns a malformed response, your agent will fail loudly instead of giving you a false positive.

Investigate Issues with Confidence

Start an investigation with a list of all current problems using `list_open_issues`. Because you're using Pydantic AI, you get a typed list of issue objects, making it easy to filter and sort in your Python code. From there, your agent can dig deeper into a specific problem with `get_issue_group`. The response is validated, so you know all the required fields for the detailed issue view are present. This prevents runtime errors in downstream code that depends on that data structure.

Setup guide

Set up Aikido Security 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": {
        "aikido-security-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Aikido Security 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 Aikido Security. 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 Aikido Security 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 Aikido Security MCP in Pydantic AI

Pydantic AI automatically creates Pydantic models from the MCP Server's schema. When your agent gets a response from an Aikido Security tool, it parses the JSON into one of these models. If the data doesn't match the expected types or structure, it raises an exception.

Yes, Pydantic AI is model-agnostic. You can use it with models from OpenAI, Anthropic, Google, or even a local model you're running yourself. It just handles the tool-calling and response validation for the Aikido Security MCP server.

After installing `pydantic-ai-slim[mcp]`, you create an `MCPToolset` instance with your Vinkius MCP server URL. Then you pass this toolset to your agent's constructor. It’s a clean way to add all the Aikido Security tools at once.

Choose it if you prioritize correctness and reliability. If your application can't tolerate silent failures or unexpected API changes from Aikido Security, Pydantic AI's runtime validation is a critical safety net. It's for building robust, predictable security automation.

The server provides access to your Aikido security metadata, like vulnerability lists, repository information, and cloud asset details. Your Pydantic AI agent communicates with this data through the Vinkius endpoint, which runs in a secure, zero-trust sandbox for each request.

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