How to Use the Onpipeline MCP in Pydantic AI

Q: How do I initialize the Onpipeline MCP Server inside Pydantic AI?

Install pydantic-ai-slimmcp. Use the unified MCPToolset("http://...") class and pass it to your Agent's toolsets parameter.

Q: Why did Pydantic AI deprecate MCPServerHTTP for Onpipeline?

The framework moved to a unified MCPToolset pattern. This handles both Streamable HTTP and SSE transports under the hood without requiring separate server classes.

Q: What happens if Onpipeline returns unexpected data to Pydantic AI?

The framework catches it immediately. If getdealdetails returns a string where an integer was expected, Pydantic raises a runtime error rather than passing bad data to your application.

Connect the Onpipeline MCP Server to Pydantic AI to enforce strict type validation on every CRM read and write.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Onpipeline MCP to Pydantic AI

Create your Vinkius account to connect Onpipeline 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 Onpipeline with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Deal Creation

Sales data is useless if it is formatted incorrectly. When your agent attempts to log a new opportunity, it uses `create_crm_deal` and `create_crm_contact`. Pydantic AI validates the payload before it ever hits the MCP Server. If the agent hallucinates a currency field or forgets a required pipeline stage, the framework throws a loud validation error instead of silently corrupting your database.

Validate Complex Pipeline Reads

Pulling revenue forecasts requires exact data structures. Your agent calls `list_pipelines` followed by `list_crm_deals` to aggregate quarterly projections. Every JSON response from Onpipeline maps directly to your Pydantic models. You know exactly what fields are present, allowing you to write deterministic Python logic for your reporting.

Audit Activities via MCP Server

You might switch from Anthropic to a local model for cost savings. Because this setup is model-agnostic, your CRM integration code stays exactly the same. The agent pulls rep touchpoints using `list_activities` and `list_crm_events`. The framework ensures the output matches your expected schema, regardless of which LLM generated the underlying tool call.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Use the unified `MCPToolset("http://...")` class and pass it to your Agent's `toolsets` parameter.

The framework moved to a unified `MCPToolset` pattern. This handles both Streamable HTTP and SSE transports under the hood without requiring separate server classes.

The framework catches it immediately. If `get_deal_details` returns a string where an integer was expected, Pydantic raises a runtime error rather than passing bad data to your application.

Yes. Pydantic AI is model-agnostic. As long as your chosen model supports basic tool calling, it can interact with `list_crm_organizations` and other endpoints.

Your sales pipelines remain strictly isolated. When the framework fetches projected revenue via `list_crm_deals`, the Vinkius routing layer processes the request in a stateless sandbox that retains zero memory of your financial figures.

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