How to Use the folk MCP in OpenAI Agents SDK

Q: What's the best way to manage sales leads from folk with the OpenAI Agents SDK?

Start by having your agent fetch relevant contacts using listcontacts with a specific group ID. Then, loop through the results, use listinteractions to check for recent activity, and decide on the next action. It's a simple, powerful way to build an automated sales assistant.

Q: Can my recruiting agent built with the OpenAI Agents SDK use folk to track candidates?

Absolutely. The agent can use createcontact for new applicants and listcontactnotes to keep a running log of interviews and feedback. This keeps all your candidate relationship data organized in one place.

Build production-ready relationship management agents with the folk MCP server and the OpenAI Agents SDK's built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect folk MCP to OpenAI Agents SDK

Create your Vinkius account to connect folk to OpenAI Agents SDK 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 folk with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Contacts, Safely

Your agent can now manage your entire contact list without writing custom API code. Use `create_contact` to add new leads or candidates, then organize them into segments with `list_groups`. The OpenAI Agents SDK automatically discovers these tools. The real value is the safety net. Before your agent creates a duplicate or modifies a key contact, the SDK can prompt for confirmation. It's a reliable way to automate CRM tasks without risking your data's integrity.

Trace Every Interaction

Give your agents a perfect memory of every relationship. The `list_interactions` and `list_contact_notes` tools pull the complete history for any contact. Your agent can use this context to draft better emails or prepare for calls. Every tool call is tracked in your OpenAI dashboard. You get a full audit log showing which agent accessed what data, when, and why. This makes debugging complex multi-agent workflows much simpler.

Build Specialized Agents with the OpenAI Agents SDK

Don't build one agent that does everything. Build a sales agent that uses `create_contact` and a recruiting agent that relies on `list_contact_notes`. The OpenAI Agents SDK lets you hand off tasks between them. This folk MCP server provides the focused toolset for any agent dealing with people. You can combine it with other MCP servers to build a full-stack team of automated specialists, each with its own validated set of skills.

Setup guide

Set up folk 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 folk tools at runtime.
3

Create your Agent

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

Run the agent

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

It's automatic. You just pass the MCP server endpoint to the agent constructor. The SDK then queries the server for its available tools, like `list_contacts`, and makes them available to the agent.

Yes. The OpenAI Agents SDK allows you to define guardrails and permissions. You can create a policy that allows the agent to read data with `get_contact_details` but requires human approval before executing `create_contact`.

Start by having your agent fetch relevant contacts using `list_contacts` with a specific group ID. Then, loop through the results, use `list_interactions` to check for recent activity, and decide on the next action. It's a simple, powerful way to build an automated sales assistant.

Absolutely. The agent can use `create_contact` for new applicants and `list_contact_notes` to keep a running log of interviews and feedback. This keeps all your candidate relationship data organized in one place.

Your contact details, notes, and interaction history are streamed directly between folk and your agent through our ephemeral server. We don't store your data. The Vinkius sandbox environment ensures each request is isolated and your API token is encrypted.

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