How do I find my Affinity API Key?

Log in to Affinity, go to **Settings** > **API Keys**. You can generate or copy your existing API key from there. Ensure you are on a supported plan (Scale or higher).

What is a Relationship Strength score?

It is a numeric value from 0 to 100 calculated by Affinity based on your team's communication history. A higher score indicates more frequent and recent interactions.

Can I retrieve meeting logs via the agent?

Yes! Use the `list_interactions` tool to see recent emails and meetings that have been automatically synced to your Affinity account.

Affinity MCP Server for Pydantic AI 5 tools — connect in under 2 minutes

Name: Affinity
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 5 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Affinity through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Affinity "
            "(5 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Affinity?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Affinity MCP Server

Connect your Affinity account to your AI agent to unlock professional relationship intelligence and CRM orchestration. From auditing your smart lists to monitoring recent email and meeting interactions and managing your contact pipeline, your agent handles your deal flow through natural conversation.

Pydantic AI validates every Affinity tool response against typed schemas, catching data inconsistencies at build time. Connect 5 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Smart List Management — List and retrieve entries for your custom smart lists, including statuses and field values
Relationship Intelligence — Access relationship strength scores and identify 'warm' introduction paths within your network
Contact Oversight — List and manage people and organizations, ensuring your B2B intelligence is always up-to-date
Interaction Auditing — Retrieve logs of recent emails, meetings, and calls automatically synced from team accounts
Pipeline Insights — Quickly identify active opportunities and track deal progress directly from your chat interface

The Affinity MCP Server exposes 5 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Affinity to Pydantic AI via MCP

Follow these steps to integrate the Affinity MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 5 tools from Affinity with type-safe schemas

Why Use Pydantic AI with the Affinity MCP Server

Pydantic AI provides unique advantages when paired with Affinity through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Affinity integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Affinity connection logic from agent behavior for testable, maintainable code

Affinity + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Affinity MCP Server delivers measurable value.

Type-safe data pipelines: query Affinity with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Affinity tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Affinity and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Affinity responses and write comprehensive agent tests

Affinity MCP Tools for Pydantic AI (5)

These 5 tools become available when you connect Affinity to Pydantic AI via MCP:

list_interactions

Retrieve recent chronological logs of synced emails, meetings, and calls across your team

list_list_entries

Retrieve the people or organizations associated with a specific Affinity smart list ID

list_organizations

Retrieve companies and institutions mapped within your Affinity CRM

list_persons

Retrieve a paginated list of people your team has interacted with in your Affinity network

list_smart_lists

Retrieve the catalog of custom smart lists (pipelines) securely configured in your account

Example Prompts for Affinity in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Affinity immediately.

"Search for a person contact with the name 'Jane Smith'."

"List all entries in my 'Active Deals' smart list."

"Show me the last 5 meetings my team had with 'Innovate Corp'."

Troubleshooting Affinity MCP Server with Pydantic AI

Common issues when connecting Affinity to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Affinity + Pydantic AI FAQ

Common questions about integrating Affinity MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Affinity MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.