How to Use the Legito MCP in Pydantic AI

Q: Can I use Pydantic AI to delete Legito document records safely?

Yes. You can wrap the deletedocumentrecord tool in a custom validation step. This ensures the agent only deletes records that meet your strict safety criteria.

Q: How does Pydantic AI handle template configurations?

The agent calls listtemplatesuites and maps the response to a structured Python model. This lets you inspect template variables with full type-hinting support in your IDE.

Build type-safe document pipelines with Pydantic AI and validate contract metadata at runtime with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Legito MCP to Pydantic AI

Create your Vinkius account to connect Legito 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 Legito with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Legito contract data with Pydantic AI

Stop worrying about malformed legal documents by validating every payload before calling `create_document_version_data`. This MCP Server integrates with Pydantic AI to validate every payload before it reaches the API, ensuring inputs match strict Python schemas. If the agent attempts to pass an invalid currency or missing field, the system fails immediately with a clear validation error. This prevents corrupt records from entering your document system.

Manage user groups with runtime type safety

User management requires absolute precision when your agent uses `create_user` to build out your organization's hierarchy. Pydantic AI ensures that every user object contains the exact fields required by the API, avoiding silent failures. By validating the output of `list_users` and `list_user_groups`, your application catches API drift or unexpected null values instantly. This keeps your user directory clean and predictable.

Secure document sharing using typed schemas

Sharing legal documents must be error-free, which is why the agent calls `share_with_user` to manage document access. Pydantic AI validates the sharing payload, ensuring that user IDs and permission levels are formatted correctly. If an agent tries to assign an unsupported permission level, the runtime validation blocks the call. This prevents accidental over-sharing of sensitive contracts.

Setup guide

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

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

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

Use MCPToolset with your server's HTTP endpoint. Pass the toolset directly into the toolsets argument of your Agent constructor to start using the 31 tools.

Pydantic AI will raise a validation error if the response doesn't match the expected schema. This prevents your agent from processing corrupt document records or invalid user permissions.

Yes. You can wrap the `delete_document_record` tool in a custom validation step. This ensures the agent only deletes records that meet your strict safety criteria.

The agent calls `list_template_suites` and maps the response to a structured Python model. This lets you inspect template variables with full type-hinting support in your IDE.

All user permissions and template suites are validated locally in your Python environment. The MCP server uses an ephemeral sandbox to ensure your sensitive data is never stored or exposed to external networks.

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