How to Use the Regex Toolkit MCP in OpenAI Agents SDK

Q: How do I configure the Regex Toolkit with the OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize the MCP server using MCPServerStreamableHttp within an async context manager. Pass the server instance directly into your Agent constructor in the mcpservers list to enable automatic tool discovery.

Q: How does caching tools improve execution speed?

Setting cacheToolsList=True in your initialization parameters prevents the agent from querying the server for its tool definitions on every turn. This optimization cuts down network latency and speeds up overall agent response times.

Give your OpenAI Agents SDK production deployment deterministic regex matching to stop text processing hallucinations cold.

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 OpenAI Agents SDK

Create your Vinkius account to connect Regex Toolkit to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Stop text extraction hallucinations

The `extract_pattern` tool gives your agent a strict, non-backtracking regex engine to extract emails, URLs, and phone numbers from unstructured text. Instead of letting the LLM guess and make up phone numbers, this tool runs native regular expressions directly on the input data. When you register this MCP server with your agent, the tool outputs actual matches instantly. It filters out the noise so your production pipeline gets clean, verified strings without wasting tokens on model reasoning.

Redact PII in OpenAI Agents SDK pipelines

The `mask_sensitive_data` tool replaces emails, phone numbers, and URLs in raw text with plain `[REDACTED]` tags before those payloads hit your model. This prevents sensitive customer data from leaking into the OpenAI platform or being stored in conversational history logs. You configure this MCP Server inside your async context manager to scrub inputs automatically. It acts as an inline guardrail, intercepting raw text and returning sanitized strings so your agent never processes raw PII.

Strict format validation for agent actions

The `validate_pattern` tool checks whether a user-provided string strictly conforms to standard email, URL, or telephone formats. It returns a simple boolean match status instead of letting the agent guess if a string looks correct. By using this validation check, you can halt execution or trigger a correction loop before the agent commits an invalid string to your database. This keeps your application state clean and prevents bad data from breaking downstream processes.

Setup guide

Set up Regex Toolkit 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 Regex Toolkit tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Regex Toolkit 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="Regex Toolkit Agent",
            instructions="You have access to Regex Toolkit 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 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 OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize the MCP server using `MCPServerStreamableHttp` within an async context manager. Pass the server instance directly into your `Agent` constructor in the `mcp_servers` list to enable automatic tool discovery.

Yes, you can control tool access by filtering the registered tools or by defining specific agent schemas. However, because this MCP server only exposes three utility tools, leaving them all active has negligible overhead on performance.

Yes, the server uses a safe, non-backtracking matching engine to prevent regular expression denial of service attacks. This design ensures that malicious text inputs cannot hang your agent's execution thread or crash your production server.

Setting `cacheToolsList=True` in your initialization parameters prevents the agent from querying the server for its tool definitions on every turn. This optimization cuts down network latency and speeds up overall agent response times.

Your raw text, phone numbers, and email strings are processed entirely within an isolated V8 sandbox on Vinkius. No data is stored, logged, or sent to third-party endpoints, ensuring your PII stays completely private during extraction.

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