How to Use the DISCO MCP in Pydantic AI

Q: Can I use Pydantic AI to list all documents in a DISCO matter?

Yes. The listmatterdocuments tool returns a validated list of files. Pydantic AI checks the response against your model, ensuring every document object is correctly formatted.

Q: How do I search for evidence with DISCO in Pydantic AI?

You call searchmatterdocuments with your query parameters. The results are automatically validated as a list of document objects, allowing you to iterate through them safely.

Use Pydantic AI for type-safe legal operations. Get validated DISCO data inside your agents with full runtime schema enforcement.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DISCO MCP to Pydantic AI

Create your Vinkius account to connect DISCO 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 DISCO with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe legal matter access

Pydantic AI ensures every response from your legal server matches your expected schema. Use `list_legal_matters` to see your cases, and the framework will fail if the structure isn't perfect. This eliminates the risk of silent errors when handling complex legal data. You get validated records every time, which keeps your agent's logic stable.

Structured document analysis for Pydantic AI

Extracting information from legal files requires precision. Use `get_document_metadata` to receive typed objects that your agent can process without hallucinating fields. This approach turns messy API responses into clean, typed Python objects. It makes your agent's code easier to maintain and much less prone to runtime crashes.

Granular user and tag management

Handle your matter tags and user access lists with strict validation. Use `list_document_tags` to categorize evidence and `list_matter_access_users` to verify permissions. Because Pydantic AI validates these lists at runtime, you can be sure your agent is operating on correct, current data. It provides the type safety you need for production-grade legal ops.

Setup guide

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

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

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

It uses your defined Pydantic models to verify every field returned by the server. If the DISCO API returns data that doesn't match your schema, the agent stops immediately to prevent errors.

Yes. The `list_matter_documents` tool returns a validated list of files. Pydantic AI checks the response against your model, ensuring every document object is correctly formatted.

You call `search_matter_documents` with your query parameters. The results are automatically validated as a list of document objects, allowing you to iterate through them safely.

The server returns an error code. Pydantic AI catches this, allowing you to define a fallback or log the failure before it affects your agent's state.

Your metadata is handled only within the scope of your requested tool calls. Pydantic AI ensures the data structure is correct without exposing your sensitive account credentials to unauthorized logs.

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