How to Use the Sansan MCP in Mastra AI

Build resilient contact management workflows in Mastra AI using the Sansan MCP Server.

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 Mastra AI

Create your Vinkius account to connect Sansan to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Mastra AI workflows for Sansan contacts

The `get_biz_card` tool pulls exact scanned card details into your Mastra AI workflow engine. You build conditional branches that check if a phone number exists on the card. If it fails, the framework automatically retries or escalates the task to an administrator using built-in backoff logic. You pass `list_persons` into a multi-step sync pipeline. The agent fetches the contact list, compares it against your internal CRM, and updates missing fields. You get a bulletproof background process that handles rate limits and network drops without human intervention.

Map organizational data with human oversight

The `list_departments` tool exposes corporate hierarchies to your agent. When the agent decides to reassign a batch of contacts based on department changes, you can enforce the requireToolApproval flag. This pauses the execution until a human reviews the proposed organizational shift. Calling `list_users` alongside `get_person` lets the workflow verify which internal employee owns a specific external contact. The MCP Server executes these lookups across thousands of records. Mastra manages the sequence, ensuring every lookup completes before the next step begins.

Automate tag-based segmentation

The `list_tags` tool feeds your agent the exact categorization labels applied to physical business cards. Your script watches for new tags, triggering `list_biz_cards` to grab the associated records. The framework routes these segmented lists into targeted email campaigns or reporting dashboards. You deploy this entire contact segmentation logic to any cloud provider with a single command. The agent uses `search_biz_cards` to dynamically update segments based on live queries. You stop writing custom cron jobs and let the state machine handle the execution schedule.

Setup guide

Set up Sansan MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Sansan tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "sansan-mcp-client",
  servers: {
    "sansan-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Sansan Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Sansan tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Sansan transactions"
);
console.log(result.text);

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 Mastra AI

Install @mastra/mcp@latest. Instantiate an MCPClient with your server URL, call listTools(), and spread the results into your agent's tool array. The framework auto-detects whether to use SSE or HTTP transport.

Yes. You enable requireToolApproval on specific tools like get_person. The workflow halts, waits for your manual confirmation, and then proceeds with the contact data.

The framework catches the failure and applies exponential backoff. It retries the tool execution automatically before throwing a fatal error, protecting your sync jobs from temporary network blips.

You instruct the agent in its system prompt to loop through the list_biz_cards results. The workflow engine maintains the state across multiple tool calls until the full list is processed.

This integration processes internal department mappings and employee names. Vinkius runs every request in an ephemeral sandbox that vaporizes after the transaction. We hold zero persistent logs of your organizational structure.

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