How to Use the Affinity MCP in Pydantic AI

Q: How do I configure Affinity with Pydantic AI?

Install pydantic-ai-slimmcp via pip. Create an MCPToolset with your Vinkius HTTP endpoint URL, then pass it in the toolsets array when building your agent.

Bring strict type safety to your Affinity MCP Server data with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinity MCP to Pydantic AI

Create your Vinkius account to connect Affinity 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 Affinity with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Pydantic AI queries

Silent data corruption kills production pipelines. When your agent calls `list_organizations` or `list_persons`, the returned CRM records get validated immediately against your defined Python models. If the Affinity API returns an unexpected field type, the framework fails loudly instead of hallucinating a fix. This model-agnostic approach means you can swap LLMs without rewriting your data structures. You might run Anthropic today and a local model tomorrow. The validation layer stays exactly the same, ensuring your relationship graphs always match your expected schema.

Validate deal pipelines

Managing custom deal stages requires exact data matching. Your script uses `list_smart_lists` to pull the pipeline catalog, followed by `list_list_entries` to grab the associated people and companies. Every single entry must pass runtime validation before your agent acts on it. Setting this MCP Server up requires the unified MCPToolset approach pointing to your HTTP endpoint. The older server classes are deprecated, so you just pass the toolset to your agent and let the strict validation handle the rest.

Audit team interactions

Pulling historical communication logs demands high accuracy. The `list_interactions` tool grabs chronological logs of synced emails, meetings, and calls across your team via the MCP Server. Your agent processes these logs knowing every timestamp and participant ID matches your strict type definitions. You care about correctness more than raw speed here. Forcing the LLM to adhere to strict Pydantic models ensures your automated CRM audits never generate fake meeting notes or invent non-existent relationships.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp] via pip. Create an MCPToolset with your Vinkius HTTP endpoint URL, then pass it in the toolsets array when building your agent.

Every response from the MCP Server gets checked at runtime. If a smart list entry returns an unexpected data type, your script throws a validation error immediately.

The framework is entirely model-agnostic. You can use local LLMs, OpenAI, or Gemini to parse your CRM data as long as the outputs match your schemas.

The agent fails loudly. You get a strict Pydantic validation error rather than letting the LLM silently ingest malformed contact records.

Vinkius manages the authentication behind a zero-trust V8 Isolate Sandbox. Your team's synced emails and proprietary deal pipelines stay strictly confined to ephemeral sessions that require a valid endpoint token.

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