How to Use the Clari MCP in Pydantic AI

Q: What's the setup for connecting Clari and Pydantic AI?

Install pydantic-ai-slimmcp. Then, create an MCPToolset instance with your Vinkius server URL. You pass that toolset into the toolsets list when you create your Pydantic AI agent.

Build type-safe Clari agents with Pydantic AI. Get validated, structured revenue data from your MCP Server, or fail with a clear error.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clari MCP to Pydantic AI

Create your Vinkius account to connect Clari 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 Clari with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Revenue Data, Every Time

When you ask your agent for opportunity details with `get_opportunity_revenue_details`, you need the right data structure. Pydantic AI enforces this. If the API ever changes or returns something unexpected, your code will raise a `ValidationError` instead of silently failing or passing bad data downstream. This is a fundamentally different way to build agents. Instead of hoping the LLM correctly interprets a blob of JSON, you get a Pydantic model populated with Clari's data. It makes your agent's logic simpler and far less brittle.

Build Model-Agnostic Sales Bots

Your agent can pull forecasts with `list_clari_forecasts` or check export job status with `list_clari_export_jobs`. Because Pydantic AI isn't tied to one model provider, you can swap between OpenAI, Anthropic, or a local LLM without rewriting your tool logic. The Clari integration will work the same way. The `MCPToolset` makes this easy. You give it the Vinkius URL, add it to your agent, and Pydantic AI handles the rest. It fetches the server's OpenAPI spec, generates Pydantic models on the fly, and uses them to call the tools and validate the responses.

A Reliable MCP Server for Clari

This isn't just for deal data. You can build reliable internal admin bots. Have an agent that uses `list_clari_users` and `list_clari_audit_logs` to generate weekly reports on user activity. You can trust the output because every field has been validated. The whole point of Pydantic AI is correctness. This MCP Server gives you a reliable source of Clari data, and the framework guarantees that what your agent works with is exactly what you expect. No more parsing messy JSON or writing defensive code to handle missing keys.

Setup guide

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

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

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

Pydantic AI fetches the MCP Server's schema and generates Pydantic models for each tool's output. When your agent calls a Clari tool, the JSON response is parsed and validated against that model. If anything is missing, extra, or the wrong type, it raises an error.

Yes. Pydantic AI is model-agnostic. As long as your local model can handle function calling, you can connect it to the Clari `MCPToolset` and it will work just like a cloud-based model.

Install `pydantic-ai-slim[mcp]`. Then, create an `MCPToolset` instance with your Vinkius server URL. You pass that toolset into the `toolsets` list when you create your Pydantic AI agent.

Yes, it works with Streamable HTTP and SSE transports. This means your agent can process data from Clari as it arrives, which is great for building responsive, conversational interfaces.

Your agent requests specific Clari data points like opportunity details, forecast history, and user information. That data passes through the Vinkius server, which runs in a secure, isolated sandbox, and is validated by your Pydantic AI client before use. No revenue or user data is ever stored by Vinkius.

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