How to Use the Indy MCP in Pydantic AI

Q: How do I initialize the Indy MCP Server toolset in Pydantic AI?

Use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset directly to your Agent constructor to expose the 12 tools.

Q: Can Pydantic AI manage my Indy user directory?

Yes, the agent can call listusers to fetch active team members. The framework validates each user object against a strict internal schema before processing.

Q: How is my freelance user data secured when using Pydantic AI?

Every API call to getuser runs through Vinkius's zero-trust gateway. Your freelance user profiles are never cached or exposed to external networks, maintaining strict client confidentiality.

Enforce strict runtime type-safety over your Indy freelance workflows using this MCP Server with the Pydantic AI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Indy MCP to Pydantic AI

Create your Vinkius account to connect Indy 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 Indy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Form Management with Pydantic AI

The `get_form` tool retrieves form schemas and validates the structure against strict Python type definitions at runtime. This integration ensures that your Pydantic AI agent never processes corrupted or malformed layout data. If a form configuration changes on the platform, the framework fails loudly before executing down-stream logic. This prevents silent failures in your client onboarding pipeline by ensuring every field matches your code's expectations.

Validating Freelance Submissions at Runtime

Data integrity is guaranteed when the `list_records` tool pulls raw submissions directly into Pydantic models using this MCP Server integration. Your Pydantic AI agent parses client budgets, contact details, and project specs with absolute type certainty. When digging into a specific submission with `get_record`, any missing field triggers an immediate validation error. You write clean, type-hinted code knowing that your agent will never hallucinate client details.

Strict Webhook Lifecycle Control

Payload structures are validated against your predefined schemas immediately after the `create_webhook` tool registers a new event listener. This means your Pydantic AI agent only handles verified webhook events, ignoring malformed network requests. To clean up your environment, the agent uses `delete_webhook` to remove inactive endpoints once a client onboarding sequence finishes. The entire process is model-agnostic, running reliably whether you use local models or commercial APIs.

Setup guide

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

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

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

Use the unified `MCPToolset` class with your Vinkius HTTP endpoint. Pass this toolset directly to your Agent constructor to expose the 12 tools.

The framework raises a validation error immediately instead of passing bad data to your agent. This keeps your database clean and free of corrupt records.

Yes, the agent can call `list_users` to fetch active team members. The framework validates each user object against a strict internal schema before processing.

The agent validates the returned form object using a Pydantic model to confirm the creation succeeded. This ensures you always get a valid form ID for future steps.

Every API call to `get_user` runs through Vinkius's zero-trust gateway. Your freelance user profiles are never cached or exposed to external networks, maintaining strict client confidentiality.

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