Can the assistant create new Retool apps or modify queries?

No, this integration is primarily focused on querying and auditing your Retool workspace. It can list apps (`list_apps`), detail definitions (`get_app`), and trace infrastructure (`list_resources`, `list_workflows`) but cannot currently modify app UI or delete users.

Where do I find the Retool Domain?

Your Retool domain is exactly what you see in the URL bar when you log into Retool. For example, if you access Retool at `https://acme-corp.retool.com`, your domain is `acme-corp.retool.com`. For self-hosted deployments, use the root domain of your custom instance.

Can the AI show me which automated workflows are currently active?

Yes. Use `list_workflows` to retrieve all automation workflows configured in your Retool workspace, including their names and status. This lets you quickly verify which background processes are running without opening the Retool dashboard.

Retool MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Retool
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Retool through the 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 Retool "
            "(7 tools)."
        ),
    )

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

Connect your conversational assistant directly to the Retool ecosystem. This integration enables your AI to explore the organizational structure of your internal tools, auditing who has access to what, and reviewing which databases are connected.

Pydantic AI validates every Retool tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the 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

Audit Applications — Ask your assistant to scan your Retool workspace (list_apps) and drill down into the configuration of specific tools (get_app). Observe how tools are organized by requesting a view of the folder hierarchy (list_folders).
Manage Permissions & Users — Review the active members of your Retool organization (list_users) and understand their access levels by listing the existing permission groups (list_groups).
Review DevOps & Infrastructure — Command the AI to inspect which data sources or APIs are wired into your operational stack (list_resources), and list any active background automation tasks (list_workflows).

The Retool MCP Server exposes 7 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 Retool to Pydantic AI via MCP

Follow these steps to integrate the Retool 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 7 tools from Retool with type-safe schemas

Why Use Pydantic AI with the Retool MCP Server

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

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

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

Retool + Pydantic AI Use Cases

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

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

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

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

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

Retool MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Retool to Pydantic AI via MCP:

get_app

Retrieves details for a specific Retool application

list_apps

Lists all applications in the Retool organization

list_folders

Lists all folders in the Retool workspace

list_groups

Lists all permission groups

list_resources

Lists all data resources configured in Retool

list_users

Lists all users in the Retool organization

list_workflows

Lists all Retool Workflows

Example Prompts for Retool in Pydantic AI

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

"List all users in my Retool workspace."

"List all applications currently configured."

"Tell me what resources are connected to our Retool."

Troubleshooting Retool MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Retool + Pydantic AI FAQ

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