How to Use the Agile CRM MCP in Pydantic AI

Q: What happens if the Agile CRM API changes when using Pydantic AI?

Your agent will stop and raise a ValidationError the next time it calls a tool like listdeals. This prevents your application from running with incorrect or malformed data, protecting you from silent failures.

Q: How do I set up the Agile CRM MCP server with Pydantic AI?

First, pip install "pydantic-ai-slimmcp". Then, instantiate the MCPToolset with your Vinkius server URL and pass it to your agent's toolsets list. The tools are discovered automatically.

Build reliable agents with Pydantic AI that read Agile CRM data without silent failures or data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agile CRM MCP to Pydantic AI

Create your Vinkius account to connect Agile CRM 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 Agile CRM with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe CRM Data, Guaranteed

When your agent calls a tool like `list_contacts`, you're not just getting a blob of JSON back. Pydantic AI automatically validates the response from the Agile CRM server against a strict Pydantic model at runtime. If the API ever returns an unexpected field or a missing value, your code doesn't just stumble forward with bad data. It fails loudly with a `ValidationError`. This guarantees that your agent is always working with data that matches the exact structure you expect.

Build Predictable Sales Workflows

Chain together operations on your Agile CRM data with confidence. You can have your agent `list_deals`, then pass that validated data to another function that uses `list_tasks` to find associated follow-ups for each deal. Because every tool's output is checked, you prevent data integrity issues from cascading through your agent's logic. This focus on correctness is perfect for building workflows that need to be right every time, not just most of the time.

Use Any Model with Pydantic AI

This server works with any LLM you've configured in Pydantic AI. Whether you're using OpenAI, Anthropic, Gemini, or a model running on your own machine, the experience is the same. The `MCPToolset` provides a standard way to interact with Agile CRM. Your agent gets structured, validated data from the MCP server regardless of the reasoning engine behind it. This lets you focus on your agent's logic instead of writing custom, model-specific data parsing code for your CRM tools.

Setup guide

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

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

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

It validates every API response from the Agile CRM tools against a Pydantic model. If the data doesn't match the expected schema—for example, a field is missing from a contact record—it raises a `ValidationError` immediately.

Yes. Pydantic AI is model-agnostic. As long as you've configured it to use your local model, the `MCPToolset` for Agile CRM will work without any changes.

Your agent will stop and raise a `ValidationError` the next time it calls a tool like `list_deals`. This prevents your application from running with incorrect or malformed data, protecting you from silent failures.

First, `pip install "pydantic-ai-slim[mcp]"`. Then, instantiate the `MCPToolset` with your Vinkius server URL and pass it to your agent's `toolsets` list. The tools are discovered automatically.

The server reads your contact records, sales deals, and task lists from Agile CRM. Your data's security is protected because Vinkius handles authentication with a dedicated token, and the server instance itself is ephemeral—it's created for your request and destroyed immediately after.

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