How to Use the Affinity MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup read Affinity smart lists?

Yes. The listsmartlists tool exposes your custom pipelines directly to the agent. It reads the catalog of configured lists so your code can target specific deal stages.

Give your OpenAI Agents SDK production-ready access to Affinity relationship intelligence and CRM data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinity MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build OpenAI Agents SDK pipelines

You need your production agent to map out who knows who before a big meeting. Passing the Affinity MCP Server to your agent constructor gives it immediate access to your entire network graph. The `list_persons` and `list_organizations` tools let your agent pull exact contacts and company profiles straight into the prompt context. Handoffs make this powerful. One specialized agent can run `list_smart_lists` to find active deal pipelines, then pass that data to a secondary agent that cross-references it with internal company documents. You get full visibility into every CRM query through the OpenAI dashboard tracing.

Audit team relationships

Nobody wants an agent hallucinating meeting histories. The `list_interactions` tool pulls chronological logs of synced emails, calls, and meetings directly from the source. Your agent reads the actual communication timeline instead of guessing. Built-in guardrails validate these actions before execution. If an agent tries to pull data outside its defined scope, the framework catches it. You control exactly which relationship metrics feed into your production system.

Manage deal flow automatically

Tracking moving parts across multiple accounts takes constant manual effort. Your agent can hit `list_list_entries` to pull the exact people and organizations attached to specific Affinity smart list IDs. This means your script knows exactly who sits in which pipeline stage right now. Setting `cacheToolsList=True` keeps your agent running fast across these queries. Your Python application pulls live pipeline states, formats the updates, and pushes them to your team without anyone opening a browser tab.

Setup guide

Set up Affinity 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 Affinity tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Create an MCPServerStreamableHttp object pointing to your Vinkius endpoint, then pass it in the mcp_servers list when initializing your agent.

Yes. The list_smart_lists tool exposes your custom pipelines directly to the agent. It reads the catalog of configured lists so your code can target specific deal stages.

The server itself just provides the tools, while the framework handles the routing. One agent can pull CRM data and pass that context directly to another specialized agent.

You define specific guardrails in your agent setup. If you only want it reading list_organizations, you configure the agent constraints to block the other tools.

Vinkius isolates every connection in a V8 sandbox. Your team's synced emails, call logs, and network graphs stay protected behind an ephemeral session that requires a single endpoint token to access.

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