How to Use the Clientjoy MCP in Pydantic AI

Q: How do I register the Clientjoy MCP Server with Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets argument when initializing your agent.

Q: Does Pydantic AI validate Clientjoy invoice data at runtime?

Yes, every payload from listagencyinvoices is validated against strict schemas. If a field doesn't match, the framework raises a validation error instead of passing bad data.

Q: Is the old MCPServerHTTP class still supported for Clientjoy?

No, MCPServerHTTP is deprecated. You should use the unified MCPToolset class to connect your agent to the Clientjoy MCP tools.

Run type-safe, validated Clientjoy CRM queries with Pydantic AI to guarantee zero data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clientjoy MCP to Pydantic AI

Create your Vinkius account to connect Clientjoy 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 Clientjoy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Clientjoy Leads in Pydantic AI

The `list_clientjoy_leads` and `get_lead_crm_details` tools guarantee that every lead record returned to your agent matches your strict Python type definitions at runtime. If the API returns an unexpected null value, the framework catches it instantly. This strict schema enforcement prevents your agent from hallucinating missing contact details or processing corrupted sales pipelines. You get clean, validated Pydantic models back from every single call.

Parse Clientjoy Invoices with Pydantic AI

The `list_agency_invoices` and `list_sales_quotes` tools let you run financial checks with zero fear of silent validation failures. Your agent pulls financial data and parses it directly into structured Python objects. Since this MCP Server runs externally, you connect to it using the unified `MCPToolset` class. The framework automatically validates the invoice schemas before your agent can even attempt to process them.

Type-Safe Workspace Queries via Pydantic AI

The `get_my_clientjoy_profile` and `list_clientjoy_contacts` tools allow your agent to verify active workspace users and client directories. Every response is verified against the server's strict JSON schema. This setup ensures that your agent never tries to assign a project to a non-existent contact. If the schema changes or data is malformed, Pydantic AI raises an error immediately so you can fix it.

Setup guide

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

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

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

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` argument when initializing your agent.

Yes, every payload from `list_agency_invoices` is validated against strict schemas. If a field doesn't match, the framework raises a validation error instead of passing bad data.

Yes, Pydantic AI is model-agnostic. You can run your validated CRM queries using local models, OpenAI, or Anthropic while maintaining strict type safety.

No, `MCPServerHTTP` is deprecated. You should use the unified `MCPToolset` class to connect your agent to the Clientjoy MCP tools.

Your contacts, projects, and invoices are fetched over encrypted SSE or HTTP transports directly to your running Python process. Vinkius secures the MCP transport layer, ensuring no credentials or client details are exposed.

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