How to Use the Close MCP in Pydantic AI

Q: What happens if the Close API schema changes and I'm using Pydantic AI?

Your agent will fail loudly with a ValidationError on the first call to the changed tool. This is a good thing. It prevents bad data from getting into your system and tells you exactly where the contract between your code and the API broke.

Q: How do I set up the Close integration?

Install pydantic-ai-slimmcp and then create an MCPToolset instance with your Vinkius server URL. Pass this toolset into your Agent's constructor. It's the modern, unified way to do it.

Get type-safe access to your Close CRM data with Pydantic AI. Stop guessing API schemas and get validated objects every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close MCP to Pydantic AI

Create your Vinkius account to connect Close to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Close with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get structurally reliable CRM data

This is the whole point of using Pydantic AI. When your agent calls `get_lead_details` or `get_opportunity_details`, the JSON response is automatically parsed and validated against a Pydantic model. You work with clean, predictable Python objects. If the Close API ever returns an unexpected field or data type, your code won't fail silently. Pydantic AI will raise a `ValidationError` immediately. That means you find out about data issues right away, not three functions later with a cryptic `KeyError`.

Use any LLM to access your Close data

Pydantic AI is model-agnostic, so you're not locked into one provider. You can use this Close MCP Server with an agent powered by OpenAI, Gemini, Anthropic, or even a local model running on your machine. The framework handles the tool-calling abstractions for you. Your code just defines the task, and Pydantic AI figures out how to call tools like `list_close_leads` or `list_close_tasks` using the LLM you've chosen.

Build internal tools you can actually trust

Use this MCP Server to build dependable internal bots and scripts. An agent can call `list_close_pipelines` and `list_close_opportunities` to generate a daily sales report. You can trust that report's structure because Pydantic guarantees it. This approach is perfect for scheduled jobs or simple automations where correctness is key. You write less defensive code because the framework is already doing the heavy lifting of data validation for you.

Setup guide

Set up Close 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": {
        "close-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Close 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 Close. 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 Close 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 Close MCP in Pydantic AI

Pydantic AI doesn't check for correctness, it enforces structural validity. When a tool like `get_lead_details` returns data, Pydantic AI automatically attempts to parse it into a corresponding Pydantic model. If the data's shape or types don't match the model, it raises a validation error instantly.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible instructor client for your local LLM, you can build an agent that uses this MCP Server to interact with your Close account.

Your agent will fail loudly with a `ValidationError` on the first call to the changed tool. This is a good thing. It prevents bad data from getting into your system and tells you exactly where the contract between your code and the API broke.

Install `pydantic-ai-slim[mcp]` and then create an `MCPToolset` instance with your Vinkius server URL. Pass this toolset into your `Agent`'s constructor. It's the modern, unified way to do it.

Your agent's access to customer lead and opportunity records is secured in two ways. First, all API calls go through the Vinkius sandbox, which isolates each request. Second, Pydantic AI's runtime validation acts as a client-side security check, ensuring that only data matching your explicit models gets processed by your application.

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