How to Use the Equixly MCP in Pydantic AI

Q: Can my Pydantic AI agent handle file uploads for Equixly API specs?

Yes. The agent uses the uploadapispec tool, passing the raw schema string and format. The framework validates the input parameters before sending them.

Q: How do I list historical runs on the MCP Server for a specific API target?

Call listscans with the service ID. The tool returns a validated list of past security runs, including start times and total vulnerability counts.

Secure your APIs with type-safe security agents using Equixly tools validated at runtime by Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equixly MCP to Pydantic AI

Create your Vinkius account to connect Equixly 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 Equixly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch verified vulnerability data in Pydantic AI

The `get_scan_findings` tool downloads the complete list of exploitable vulnerabilities found during a pentest run. Pydantic AI validates the structure of each finding, including the severity and HTTP evidence, before your agent processes it. You get clean, typed objects over MCP containing exact exploit steps and remediation advice. This strict validation prevents your agent from breaking when parsing complex nested JSON payloads.

Inventory your API targets via MCP Server

The `list_services` tool returns a structured list of all registered API targets, including their base URLs and discovered endpoints. This lets your agent map out the entire attack surface before deciding where to run tests. To inspect a single configuration, the agent calls `get_service` to retrieve its metadata. If a target is missing, the agent can use `create_service` to register it instantly.

Launch and monitor type-safe pentest scans

The `trigger_scan` tool starts an autonomous security scan to test your endpoints for authorization and authentication flaws. Your agent receives a validated confirmation object containing the new scan ID. You can monitor the progress of the run by calling `get_scan` with the returned ID. This returns typed fields showing total requests made, endpoints explored, and current severity metrics.

Setup guide

Set up Equixly 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": {
        "equixly-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Pydantic AI enforces strict runtime validation on all 10 tools. If the server returns unexpected vulnerability data, the framework catches it immediately instead of letting your agent hallucinate.

Use the unified MCPToolset class pointing to your server URL. Pass this toolset directly to your Agent constructor to expose the security tools.

Yes. The agent uses the `upload_api_spec` tool, passing the raw schema string and format. The framework validates the input parameters before sending them.

Call `list_scans` with the service ID. The tool returns a validated list of past security runs, including start times and total vulnerability counts.

Your API specs and vulnerability reports are handled in zero-trust sandboxes. The server only processes data in memory during scan execution, ensuring your raw schema structures and exposed routes are never stored insecurely.

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