Can my AI agent find a specific business card by just a first name?

Yes. Ask the agent to run the `search_biz_cards` tool with the contact's name. It will look through all digitized cards in the shared corporate database and return the matching profiles, including their company, department, and direct contact details.

Is it possible to list only contacts from a specific department?

Yes, you can ask your agent to first execute `list_departments` to view your organizational structure, and then cross-reference those entities with the cards via natural prompts to summarize card acquisitions per department.

What is the difference between business cards and persons?

Business Cards are individual scan snapshots of physical cards acquired over time. A 'Person' represents the consolidated identity created when multiple updated cards from the same individual are merged. You can query both views via `list_biz_cards` or `list_persons`.

Sansan MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Sansan
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Sansan through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Sansan "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Sansan?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Sansan MCP Server

Connect your Sansan account to any AI agent to access your organization’s entire secure network of digitized business cards. Effortlessly manage contact relationships directly from Claude, Cursor, or your preferred MCP client.

Pydantic AI validates every Sansan tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Business Cards — List all scanned cards, retrieve comprehensive details by card ID, and search for specific contacts by name
Personnel Records — Browse individual person profiles across all captured cards and access deep contact details
Network Organization — Inspect all available tags used for structuring and organizing business cards
Enterprise Structure — List registered Sansan users and view all distinct departments within your organization

The Sansan MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Sansan to Pydantic AI via MCP

Follow these steps to integrate the Sansan MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Sansan with type-safe schemas

Why Use Pydantic AI with the Sansan MCP Server

Pydantic AI provides unique advantages when paired with Sansan through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Sansan integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Sansan connection logic from agent behavior for testable, maintainable code

Sansan + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Sansan MCP Server delivers measurable value.

Type-safe data pipelines: query Sansan with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Sansan tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Sansan and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Sansan responses and write comprehensive agent tests

Sansan MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Sansan to Pydantic AI via MCP:

get_biz_card

Retrieves details for a specific business card

get_person

Retrieves details for a specific contact person

list_biz_cards

Lists all scanned business cards

list_departments

Lists all departments in the organization

list_persons

Lists all contact persons across cards

list_tags

Lists all tags used for organizing business cards

list_users

Lists all Sansan users in the organization

search_biz_cards

Searches for business cards by name

Example Prompts for Sansan in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Sansan immediately.

"Search for a business card with the name 'Tanaka'."

"Can you list all the tag categories in our Sansan database?"

"Get the detailed person profile for the ID 'person-12345'."

Troubleshooting Sansan MCP Server with Pydantic AI

Common issues when connecting Sansan to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Sansan + Pydantic AI FAQ

Common questions about integrating Sansan MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Sansan MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.