Where do I find my Agendor API Token?

Log in to Agendor, navigate to **Menu** > **Integrações** (Integrations) > **Token da API**. You can generate and copy your unique token from there. It will be used in the `Authorization` header as `Token your-token`.

What is an 'Upsert' in Agendor?

An Upsert is a combination of Update and Insert. It allows you to send contact data, and Agendor will either create a new record or update an existing one if the email or CNPJ already exists, preventing duplicates.

Can I see my team's tasks via the agent?

Yes! Use the `list_tasks` tool to retrieve upcoming or pending tasks for any user or organization in your CRM.

Agendor MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: Agendor
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Agendor 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 Agendor "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Agendor?"
    )
    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 Agendor MCP Server

Connect your Agendor account to your AI agent to unlock professional sales orchestration and CRM management. From creating new leads and organizations to auditing your sales pipeline and managing task workflows, your agent handles your sales ecosystem through natural conversation.

Pydantic AI validates every Agendor tool response against typed schemas, catching data inconsistencies at build time. Connect 6 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

Lead & Contact Management — Create, update, and list people and organizations to keep your CRM data current
Pipeline Orchestration — List active deals, monitor sales funnels, and retrieve details for specific deal stages
Task Management — List and create tasks to ensure your team never misses a follow-up or critical deadline
Upsert Capability — Seamlessly create or update records based on email or CNPJ to prevent duplicate data entry
Sales Insights — Quickly identify high-value opportunities or overdue deals directly from your chat interface

The Agendor MCP Server exposes 6 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 Agendor to Pydantic AI via MCP

Follow these steps to integrate the Agendor 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 6 tools from Agendor with type-safe schemas

Why Use Pydantic AI with the Agendor MCP Server

Pydantic AI provides unique advantages when paired with Agendor 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 Agendor integration code

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

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

Agendor + Pydantic AI Use Cases

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

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

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

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

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

Agendor MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect Agendor to Pydantic AI via MCP:

create_organization

Instantiate a new organization record securely within Agendor

create_person

Can optionally link the person to a company. Instantiate a new person profile natively within the Agendor CRM

list_deals

Retrieve highly active sales opportunities and negotiation pipelines tracked in Agendor

list_organizations

Retrieve a directory of institutional organizations, companies, and business entities in the CRM

list_people

Retrieve a comprehensive directory of person profiles registered in your Agendor CRM

list_tasks

Retrieve the chronological queue of upcoming activities and follow-ups scheduled for the team

Example Prompts for Agendor in Pydantic AI

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

"List the last 5 people added to my Agendor CRM."

"Show me all deals in the 'Qualified' stage of my pipeline."

"Create a new organization named 'Tech Innovations' with domain 'techinn.com'."

Troubleshooting Agendor MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Agendor + Pydantic AI FAQ

Common questions about integrating Agendor 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 Agendor MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.