How to Use the ToolJet MCP in Pydantic AI

Q: What is the best way to manage data flow with ToolJet and Pydantic AI?

First, use listtables to define your expected schemas. Then, wrap all subsequent calls (querytable, insertrow) in validation logic using Pydantic models for maximum confidence.

Q: Can I automate processes with ToolJet and Pydantic AI?

Yes. You can use triggerworkflow to initiate external automation, while still relying on Pydantic's validation layer for all the data that feeds into or comes out of the database tools.

Ensure perfect data correctness when connecting to ToolJet with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ToolJet MCP to Pydantic AI

Create your Vinkius account to connect ToolJet 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 ToolJet with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Data Retrieval

When the agent calls `query_table`, you don't have to worry about receiving malformed JSON. Because of Pydantic, every response is validated against a model at runtime. If the data structure shifts, your agent fails loudly. This means no silent corruption; you know immediately if the API returned unexpected fields or types.

Validated Record Creation

You're building mission-critical agents, so correctness matters. Use `insert_row` to write data, and Pydantic ensures that the input you provide matches your expected schema before it even hits the database. The agent can confidently assume the structure of the outgoing payload because it was validated first.

Schema Inspection and Workflow Triggers

Before writing anything, check what's available. `list_tables` shows you the schema, which is critical for building correct prompts. Plus, using `trigger_workflow` lets your agent execute complex logic while maintaining type safety across tool calls. This combination keeps the entire data flow rigorous and auditable.

Setup guide

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

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

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

The framework validates all inputs and outputs from the MCP Server. When using `query_table` or `insert_row`, you get guaranteed, type-safe Python objects back—no more dealing with messy dictionaries.

It's the main selling point. Pydantic enforces strict validation at runtime. If `query_table` returns something that doesn't match your defined schema, the agent fails with an explicit error message, not just bad data.

First, use `list_tables` to define your expected schemas. Then, wrap all subsequent calls (`query_table`, `insert_row`) in validation logic using Pydantic models for maximum confidence.

Yes. You can use `trigger_workflow` to initiate external automation, while still relying on Pydantic's validation layer for all the data that feeds into or comes out of the database tools.

This server manages structured relational data stored in a database table. The agent interacts with defined field types, ensuring every row read via `query_table` or written by `insert_row` conforms to the expected schema.

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