How to Use the Digify MCP in Pydantic AI

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

Install the package using pip install "pydantic-ai-slimmcp" and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets parameter when creating your Agent.

Q: Is the older MCPServerHTTP class still supported for Digify integration with Pydantic AI?

No, MCPServerHTTP is deprecated. You should use the unified MCPToolset("http://...") approach to connect your external server to Pydantic AI agents.

Q: How does Pydantic AI secure my Digify data room logs and file permissions?

Your document access logs, guest lists fetched by listdataroomguests, and webhook details from listwebhooks are validated locally in memory against your Pydantic schemas. Data is transmitted securely via HTTPS through Vinkius's zero-trust MCP sandbox, ensuring your file details are never stored or exposed to external networks.

Build type-safe document security pipelines using Pydantic AI and our managed MCP Server to validate every file action.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Digify MCP to Pydantic AI

Create your Vinkius account to connect Digify 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 Digify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy type-safe data rooms with Pydantic AI

The `create_dataroom` tool builds structured, secure workspaces with strict input parameter validation. Pydantic AI enforces that all configuration arguments match your defined Python schemas before sending the request to the MCP server. If the agent generates an invalid room name or incorrect guest parameters during `invite_guest`, the framework raises a validation error immediately. This prevents malformed payloads from reaching your document server and causing silent API failures.

Parse document activity logs with zero runtime drift

The `list_activities` tool returns detailed interaction histories that are parsed directly into strongly-typed Pydantic models. Your agent processes these structured logs to track exactly who opened a file without risking runtime type errors. Because Pydantic AI validates the structure of every response from `get_dataroom_stats`, you can confidently run automated security checks. If the schema of the activity log deviates, the system fails loudly, protecting your downstream auditing logic.

Protect files using validated MCP Server tools

The `protect_file` tool applies security configurations to documents, requiring precise parameter structures for watermarks and restrictions. The framework validates these options at runtime, ensuring your agent never shares a file without active protection. You configure this by passing your `MCPToolset` initialized with your Vinkius HTTP URL directly to your `Agent` instance. This unified approach ensures all tools, including `get_file` and `list_files`, adhere to strict type constraints across any LLM backend.

Setup guide

Set up Digify 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": {
        "digify-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` parameter when creating your `Agent`.

Pydantic AI will raise a validation error at runtime if the response from tools like `get_account_info` doesn't match the expected schema. This prevents corrupt data from silently polluting your agent's context.

Yes, the framework is model-agnostic. You can run your document workflows using OpenAI, Anthropic, or local models while maintaining strict type-safety for tools like `list_datarooms`.

No, `MCPServerHTTP` is deprecated. You should use the unified `MCPToolset("http://...")` approach to connect your external server to Pydantic AI agents.

Your document access logs, guest lists fetched by `list_dataroom_guests`, and webhook details from `list_webhooks` are validated locally in memory against your Pydantic schemas. Data is transmitted securely via HTTPS through Vinkius's zero-trust MCP sandbox, ensuring your file details are 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