How to Use the Sansan MCP in LangChain

Connect LangChain chains directly to your Sansan network to automate contact lookups and data flow across your pipelines.

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 LangChain

Create your Vinkius account to connect Sansan to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Sansan tools into LangChain logic

Pipe `get_biz_card` outputs directly into downstream processes without manual intervention. Your agent pulls raw contact data and formats it for your database. LangChain handles the sequence of tool calls while maintaining full observability. You see exactly how data moves from Sansan into your custom workflows.

Build multi-step contact retrieval chains

Use `search_biz_cards` to trigger a series of lookups based on your query. Your agent decides the order of operations to gather complete records. This setup ensures your agent retrieves only the necessary details. You avoid fetching redundant records by chaining `get_person` calls immediately after finding a match.

Integrate organizational data with MCP Server tools

Map departments and users using `list_departments` alongside other data sources in your chain. You gain a clear view of your network structure. Your LangChain agent cross-references these lists to verify contact ownership. It turns static API results into active, usable knowledge for your agents.

Setup guide

Set up Sansan MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Sansan tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "sansan-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Sansan transactions"
    })
    print(result["messages"][-1].content)

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.