How to Use the Landbot MCP in Pydantic AI

Q: Can I use Pydantic AI to control which agents can be assigned in Landbot?

Yes. You can create a Pydantic model with a Literal type containing the valid agent IDs. When your agent decides to call assignagent, Pydantic AI will validate its choice against that list, preventing assignment to an invalid agent.

Build reliable, type-safe Landbot agents with Pydantic AI. Get validated data structures for every customer interaction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Landbot MCP to Pydantic AI

Create your Vinkius account to connect Landbot 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 Landbot with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Customer Interactions

Stop guessing what the API will return. When your agent calls `get_customer` or `search_customers`, Pydantic AI automatically validates the response against a Pydantic model. If a field is missing or has the wrong type, your code gets an exception, not bad data. This means you can trust the data you're acting on. When you use the customer ID from a validated `get_customer` call to then fire `send_text_message`, you know for a fact that the ID is a valid string. No more silent failures.

Build Reliable Workflows with this MCP Server

This MCP server exposes all the tools you need to manage a conversation. Your agent can fetch chat logs with `get_messages` or hand off to a human with `assign_agent`. Pydantic AI's strength is making these handoffs robust. You can define a Pydantic model for the `assign_agent` operation, ensuring your agent only ever tries to assign to valid agent IDs that you've defined. It turns runtime risks into validation errors you can catch.

Manage Bot Configurations Safely

Your agent can inspect your Landbot configuration with confidence. The `list_bots` tool gives you an array of bot objects, and Pydantic AI ensures every object in that array matches your expected schema. This is critical for building routing logic. When your agent uses `get_bot` to retrieve details for routing, you're guaranteed to get the data structure you planned for. If Landbot's API ever changes, your agent will raise an error instead of making a bad decision.

Setup guide

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

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

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

Pydantic AI validates the JSON response from an MCP tool like `get_customer` against a model you define. If the data from Landbot doesn't match the model's schema, it raises a `ValidationError` immediately.

Yes. You can create a Pydantic model with a `Literal` type containing the valid agent IDs. When your agent decides to call `assign_agent`, Pydantic AI will validate its choice against that list, preventing assignment to an invalid agent.

By default, Pydantic models ignore extra fields, so your code won't break. If you configure the model to forbid extra fields, it will raise a `ValidationError`, alerting you to the change and protecting your agent from API drift.

Absolutely. Pydantic AI is model-agnostic. You can use it with OpenAI, Anthropic, or any local model with a compatible interface, and it will still provide the same type-safe validation for all Landbot tool calls.

The server touches customer metadata and chat messages when tools like `search_customers` and `get_messages` are used. Vinkius secures this connection; data passes through a sandboxed environment that's torn down after each operation. Your agent authenticates with a single secure 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