How to Use the Custify MCP in Pydantic AI

Q: How do I connect Custify to Pydantic AI?

Install the pydantic-ai-slimmcp package. Initialize an MCP toolset with your Vinkius HTTP endpoint and pass it to the toolsets array in your Agent setup. Do not use the deprecated MCPServerHTTP class.

Q: Can Pydantic AI search for specific Custify accounts?

The server provides the searchcustomersbykeyword tool specifically for this. Your agent can search by name or email, and the framework ensures the returned profiles match your expected data structure.

Type-safe Custify MCP Server for Pydantic AI. Catch validation errors before they break your agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Custify MCP to Pydantic AI

Create your Vinkius account to connect Custify 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 Custify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Custify data with Pydantic AI

Silent failures in customer success workflows destroy trust. When your agent calls `get_customer_details`, this MCP Server returns the health scores and segment data directly into your Pydantic models. If the API returns a string instead of an expected integer for a health score, the framework fails loudly. You never have to deal with hallucinated fields. The agent uses `list_customer_kpis` to pull metric definitions, and runtime validation guarantees the response matches your schema perfectly. You care about correctness, and this integration delivers it.

Map organizational structures safely

Building a clear picture of an enterprise client requires precise data extraction. Your agent can run `list_companies` to pull the top-level domain information, then execute `list_people` to gather contact details for every associated account. Because Pydantic AI is model-agnostic, you can swap between Claude for complex reasoning and a local model for basic data extraction. The agent hits `get_company_details` and parses the organizational attributes regardless of which LLM is driving the logic.

Execute customer success operations

Managing tasks requires reading the current state and acting on it. The agent pulls open items using `list_customer_success_tasks` and cross-references them with `search_customers_by_keyword` to ensure every high-priority customer gets attention. Adding new records is just as strict. When the agent uses `create_customer_profile`, the inputs are validated before they ever hit the server. You pass the toolset to your Agent constructor, and the unified HTTP transport handles the execution reliably.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package. Initialize an MCP toolset with your Vinkius HTTP endpoint and pass it to the toolsets array in your Agent setup. Do not use the deprecated MCPServerHTTP class.

Yes. Since the framework is model-agnostic, you can use local models to call tools like `list_customers` or `list_customer_notes`. The validation layer works exactly the same way as it does with OpenAI or Anthropic.

The server provides the `search_customers_by_keyword` tool specifically for this. Your agent can search by name or email, and the framework ensures the returned profiles match your expected data structure.

The framework will throw a validation error immediately. This strict runtime checking prevents your agent from making decisions based on malformed data or missing fields.

Customer profiles, internal notes, and KPI thresholds flow through a strictly ephemeral V8 Isolate Sandbox. Vinkius destroys the environment the moment your session ends. We never store your contact lists or health metrics.

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