How to Use the Sansan MCP in Pydantic AI

Q: How do I configure the Sansan MCP server in Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your server's HTTP URL. Pass this toolset to your Agent instance to expose the card management tools.

Q: Can I use SSE transport to connect Sansan to Pydantic AI?

Yes, the unified MCPToolset supports both Streamable HTTP and SSE transports for this MCP Server. Ensure your external server is running, and pass the correct endpoint URL to the toolset initializer.

Q: How does my agent list departments with Pydantic AI?

Your agent calls the listdepartments tool, which returns a structured list of corporate divisions. The framework validates this list against its internal schema, letting your agent navigate the organizational chart safely.

Build type-safe contact pipelines with Pydantic AI to validate Sansan business card data at runtime.

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 Pydantic AI

Create your Vinkius account to connect Sansan to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Strict type validation for Sansan card data

The `get_biz_card` tool retrieves physical card details and validates them against strict Pydantic schemas before your agent can use them. If the Sansan API returns an unexpected data format, your Pydantic AI agent fails loudly at runtime, preventing corrupt contact info from entering your database. Setup requires installing the slim package with `pip install "pydantic-ai-slim[mcp]"` and initializing the unified `MCPToolset` with your HTTP endpoint. Pass this toolset into your `Agent` constructor to enable automated schema enforcement across all eight MCP tools.

Validating person details in Pydantic AI

The `get_person` tool fetches verified contact details, mapping them directly to type-safe Python models. Your agent uses these validated schemas to ensure that phone numbers, email formats, and names strictly match your application's data requirements. This strict validation eliminates silent errors when parsing unstructured physical card data. By enforcing types at the boundary, you can safely pass contact records to downstream systems, knowing the data matches your exact structural expectations.

Type-safe search and tag categorization

The `search_biz_cards` tool finds business cards by name while returning structured search results that fit your exact model definitions. Your agent can then run `list_tags` to categorize these search results using validated organizational tags. Because Pydantic AI is model-agnostic, you can use this type-safe MCP Server with any LLM provider. The framework handles the JSON schema translation under the hood, ensuring your agent receives clean, structured data regardless of the underlying model.

Setup guide

Set up Sansan MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "sansan-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Sansan tools.",
)

result = await agent.run("List recent Sansan transactions")
print(result.output)

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 Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your server's HTTP URL. Pass this toolset to your `Agent` instance to expose the card management tools.

The framework validates the response against the tool's schema at runtime. If a required field is missing, Pydantic AI raises a validation error immediately, preventing your agent from processing incomplete contact data.

Yes, the unified `MCPToolset` supports both Streamable HTTP and SSE transports for this MCP Server. Ensure your external server is running, and pass the correct endpoint URL to the toolset initializer.

Your agent calls the `list_departments` tool, which returns a structured list of corporate divisions. The framework validates this list against its internal schema, letting your agent navigate the organizational chart safely.

The framework processes all contact data locally or via secure external model calls, while Vinkius manages the connection in a zero-trust sandbox. Your business card details and user lists are never cached or exposed to unauthorized third parties.

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