How to Use the Crisp MCP in Pydantic AI

Q: How do I use the Crisp tools with Pydantic AI?

Install pydantic-ai-slimmcp, then create an MCPToolset instance with your Vinkius server URL. Pass that toolset to your agent. The framework handles the rest, making tools like getvisitorprofile available with runtime validation.

Q: What happens if the Crisp API returns data Pydantic AI doesn't expect?

Your code will raise a ValidationError immediately. This is the main benefit—it prevents corrupted or unexpected data from propagating through your system. You get a loud, clear failure at the source.

Get type-safe, validated access to your Crisp data in Python with Pydantic AI. Stop dealing with broken API responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crisp MCP to Pydantic AI

Create your Vinkius account to connect Crisp 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 Crisp with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Crisp with Guaranteed Schemas

This MCP Server provides tools to query your Crisp account, like `list_conversations` and `get_visitor_profile`. Your agent can fetch live data about your website's visitors and their support chats. With Pydantic AI, every response from these tools is automatically parsed and validated. If the Crisp API returns an unexpected field or a malformed object, your code raises a `ValidationError` on the spot. You'll know exactly what broke and why, instead of chasing `KeyError` exceptions deep in your code.

Build Reliable, Model-Agnostic Agents

Pydantic AI is not tied to a single LLM provider. You can build your Crisp support agent using OpenAI, Anthropic, Gemini, or even a local model running on your own machine. The tools in this server will work the same way everywhere. This freedom means you can prototype with one model and deploy with another, all without changing your tool-using code. The `send_message` and `get_messages` functions remain constant, backed by Pydantic's type safety. Your integration with the MCP Server is stable, even if the agent's brain is not.

Construct Correct Payloads, Every Time

Some tools, like `send_message`, require you to pass data in a specific JSON format. Getting this right manually is a common source of bugs. Pydantic AI solves this by letting you work with Python objects instead of raw dictionaries. You define a Pydantic model for your message payload. When your agent decides to send a message, it populates the model. Pydantic AI handles the serialization, guaranteeing the JSON sent to the Crisp API is always correctly structured. It's about making invalid states unrepresentable in your code.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`, then create an `MCPToolset` instance with your Vinkius server URL. Pass that toolset to your agent. The framework handles the rest, making tools like `get_visitor_profile` available with runtime validation.

Your code will raise a `ValidationError` immediately. This is the main benefit—it prevents corrupted or unexpected data from propagating through your system. You get a loud, clear failure at the source.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible LLM running, you can connect it to the `MCPToolset` for Crisp and build a completely self-hosted support agent.

No, the MCP Server provides the schema. Pydantic AI uses this schema automatically to generate validators for the tool outputs. You just call the tool and get a validated object back.

Data like visitor profiles and conversation messages are fetched from Crisp through the Vinkius sandbox, which doesn't store anything. The data is then passed to your Pydantic AI agent, where it's validated client-side. The security benefit here is data integrity; you're protected against data structure corruption from the API.

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