How to Use the Pipeline CRM MCP in Pydantic AI

Q: How do I configure the Pipeline CRM MCP Server inside Pydantic AI?

You initialize the connection using MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your Agent constructor to expose the CRM tools.

Build type-safe Pydantic AI agents that interact with Pipeline CRM data under strict runtime validation rules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pipeline CRM MCP to Pydantic AI

Create your Vinkius account to connect Pipeline CRM to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pipeline CRM with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate sales pipeline data with Pydantic AI

The `list_pipeline_deals` tool outputs structured sales data that your Pydantic AI agent validates via our MCP Server against strict Python schemas. If the CRM returns an unexpected data type, the framework raises a validation error immediately. This type-safe execution ensures your agent never processes corrupt deal pipelines. By combining this with `get_pipeline_deal`, you guarantee that every deal ID and value matches your application's expected structure before any logic runs.

Structure contact and user directories safely

The `list_pipeline_people` tool retrieves customer profiles while enforcing type safety across your entire agentic workflow. Pydantic AI parses the API response directly into typed models, preventing silent data corruption. Your agent uses `list_pipeline_users` to map CRM users to internal account owners. The framework validates these user objects at runtime, ensuring that assignment tasks never reference non-existent or malformed user IDs.

Monitor tasks with guaranteed schema compliance

The `list_pipeline_tasks` tool provides your agent with pending actions that are instantly validated via this MCP integration against your Pydantic schemas. This ensures your automated task runners only operate on fully formed task objects. When checking historical notes via `list_pipeline_notes`, the framework verifies the structure of every text block and timestamp. This strict validation prevents your LLMs from hallucinating missing task details or history.

Setup guide

Set up Pipeline CRM 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": {
        "pipeline-crm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You initialize the connection using `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your `Agent` constructor to expose the CRM tools.

Yes, the framework fails loudly if the data returned by tools like `list_pipeline_deals` doesn't match your Pydantic models. This protects your downstream application from processing malformed CRM updates.

Yes, the framework is model-agnostic. You can connect OpenAI, Anthropic, or local models to your Pipeline CRM tools while maintaining the same strict runtime validation.

The framework raises a validation error at runtime, allowing your application to catch the exception and handle it gracefully. This prevents the agent from making decisions based on incomplete or corrupt account settings.

Your data is processed within an ephemeral, zero-trust V8 isolate sandbox on Vinkius. Sensitive fields fetched via `get_pipeline_person` or `list_pipeline_tasks` are never logged or stored, ensuring total data privacy.

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