How to Use the Sansan MCP in OpenAI Agents SDK

Q: How do I connect Sansan to the OpenAI Agents SDK?

Install the package with pip install openai-agents and instantiate MCPServerStreamableHttp. Pass this instance into your Agent constructor using the mcpservers argument to expose all eight MCP tools.

Q: Can my OpenAI Agents SDK agent search Sansan cards by tag?

Yes, your agent can run listtags to find existing organization tags and then filter results. It uses these tags to categorize contacts without requiring manual classification.

Q: How does the OpenAI Agents SDK handle tool caching for Sansan?

Set cacheToolsList=True when configuring the MCP server connection. This prevents your agent from requesting the tool schema on every turn, reducing latency during bulk card lookups.

Q: Can my agent query Sansan departments using this setup?

Yes, the listdepartments tool exposes the entire corporate hierarchy to your agent. This lets your system map out account structures and identify key decision-makers automatically.

Connect your OpenAI Agents SDK to Sansan to scan, search, and verify corporate contact networks inside production-grade agent loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sansan MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Secure card lookups via OpenAI Agents SDK

The `get_biz_card` tool pulls raw business card details directly into your OpenAI Agents SDK runtime for instant contact verification. This tool feeds verified corporate data to your agents, ensuring they work with physical card scans instead of relying on stale CRM records. You initialize the MCP server connection using `MCPServerStreamableHttp` within an async context manager. Pass the server in the `mcp_servers` list to your Agent constructor, and set `cacheToolsList=True` to eliminate redundant schema lookups during high-volume runs.

Automated network mapping with guardrails

The `list_persons` tool lets your agent scan across all contact persons to map out organizational hierarchies automatically. Because the SDK provides built-in guardrails, you can audit your agent's routing decisions before it attempts to query sensitive internal departments. When an agent needs to pivot from a high-level search to deep detail, it uses `get_person` to fetch specific contact profiles. You can configure specialized agents to handle different branches of your network tree, handing off tasks between them smoothly using the native OpenAI tracing dashboard to monitor every API step.

Targeted account search with full tracing

The `search_biz_cards` tool queries your corporate Sansan database using simple text strings to pinpoint target accounts. Your agent executes this tool to locate specific physical cards, extracting precise names and phone numbers without manual database queries. OpenAI Agents SDK tracks these search queries across your MCP Server integrations, letting you debug exactly which search parameters your agent selected. This transparency prevents silent search failures and ensures your automated outbound workflows target the correct prospects every time.

Setup guide

Set up Sansan 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 Sansan tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with `pip install openai-agents` and instantiate `MCPServerStreamableHttp`. Pass this instance into your Agent constructor using the `mcp_servers` argument to expose all eight MCP tools.

Yes, your agent can run `list_tags` to find existing organization tags and then filter results. It uses these tags to categorize contacts without requiring manual classification.

Set `cacheToolsList=True` when configuring the MCP server connection. This prevents your agent from requesting the tool schema on every turn, reducing latency during bulk card lookups.

Yes, the `list_departments` tool exposes the entire corporate hierarchy to your agent. This lets your system map out account structures and identify key decision-makers automatically.

All business card data and contact details remain inside Vinkius's isolated V8 sandbox run by the MCP Server. The OpenAI Agents SDK only receives the specific JSON payloads returned by `get_biz_card` or `get_person` over an encrypted HTTP transport, keeping raw contact databases isolated.

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