How to Use the Regex Toolkit MCP in Pydantic AI

Q: How do I integrate the Regex Toolkit with Pydantic AI?

Install the library using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with the server's HTTP endpoint. Pass this toolset into your Agent constructor using the toolsets argument.

Q: Is the legacy MCPServerHTTP class still supported?

No, the MCPServerHTTP class is deprecated. You should use the unified MCPToolset class to connect to external MCP servers over HTTP or SSE.

Enforce runtime validation on your Pydantic AI agents with deterministic regex matching that fails loudly on bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Regex Toolkit MCP to Pydantic AI

Create your Vinkius account to connect Regex Toolkit to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Regex Toolkit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Strict runtime validation for Pydantic AI

The `validate_pattern` tool asserts whether a given string is a valid email, URL, or phone number format. It returns a strict boolean value, which your agent can map directly to a Pydantic model field for instant runtime validation. This approach ensures that if a model attempts to generate or pass an invalid string, the system raises a validation error immediately. You get absolute guarantees on data integrity before any database writes occur.

Type-safe text extraction without hallucinations

The `extract_pattern` tool scans text inputs to pull out unique emails, URLs, or phone numbers. It returns these matches in structured lists, making it easy to parse them directly into type-safe Python objects. By using this MCP Server, your agent avoids relying on loose LLM parsing instructions. The deterministic regular expressions handle the extraction, leaving the model to focus on high-level reasoning.

Redact sensitive PII before model processing

The `mask_sensitive_data` tool searches your text inputs for emails, phone numbers, and URLs, replacing them with generic `[REDACTED]` tags. This ensures that your agent never sends raw PII to external language model APIs. Because Pydantic AI is model-agnostic, you can use this redaction tool across OpenAI, Anthropic, or local models. It acts as a universal privacy guardrail at the edge of your application.

Setup guide

Set up Regex Toolkit 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": {
        "regex-toolkit-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Regex Toolkit 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 regex-toolkit. 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 Regex Toolkit 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 Regex Toolkit MCP in Pydantic AI

Install the library using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with the server's HTTP endpoint. Pass this toolset into your `Agent` constructor using the `toolsets` argument.

Yes, the MCP server supports both Streamable HTTP and SSE transports. You must run the server externally and connect your agent using the unified `MCPToolset` class.

If the server returns unexpected data, the framework raises a validation error at runtime. This prevents silent corruption of your data pipelines and keeps your application state consistent.

No, the `MCPServerHTTP` class is deprecated. You should use the unified `MCPToolset` class to connect to external MCP servers over HTTP or SSE.

Yes, all text, telephone numbers, and email addresses are processed in memory within an ephemeral V8 sandbox. No data is cached or stored on disk, ensuring complete privacy for your application payloads.

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