How to Use the Sproof MCP in Pydantic AI

Q: How does Sproof and Pydantic AI handle audit logs?

The agent uses the listaudittrail tool. Because this output is validated by Pydantic, you can trust that the history records—dates, actions, users—are perfectly structured for your application.

Q: What data does Sproof and Pydantic AI touch regarding user profiles?

The getprofile tool retrieves account profile details. Since this is a Pydantic flow, the agent will receive strongly typed fields for every piece of profile data it needs.

Q: How do I list all signature requests with Sproof and Pydantic AI?

You call listsignaturerequests. The result is immediately passed through validation, ensuring that the returned list of request IDs and statuses are always in the expected format.

Q: If I'm building with Sproof and Pydantic AI, how do I manage signers?

Use listsigners to get a definitive list of participants for any request. The Pydantic validation confirms that the role and identity fields are present and correctly typed.

Q: If I'm building with Sproof and Pydantic AI, how do I confirm document details?

The agent calls getdocument to fetch file metadata. This action is guaranteed to return a structured object, making downstream processing reliable.

Build validated signing agents with Pydantic AI using Sproof's strict tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Sproof MCP to Pydantic AI

Create your Vinkius account to connect Sproof 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 Sproof with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Document Retrieval and Integrity

The agent needs to know what it’s working with. `list_documents` shows every document ID available in the system, letting your process validate its inputs early on. This prevents downstream failures. You can get deep details using `get_document`. Because Pydantic validates everything, you'll receive a structured, predictable model containing all necessary metadata.

Controlling Signature Workflows

To start a signing session, the agent executes `create_signature_request`, passing data via JSON. Pydantic ensures that payload structure is 100% correct before sending it to Sproof. If you need to stop an active workflow, use `cancel_signature_request`. The tool confirms cancellation status, giving your agent a clean boolean result for the next step.

Participant and Audit Management

Tracking activity is non-negotiable. `list_audit_trail` pulls the full history of actions taken on any request. The resulting data structure guarantees you get all required timestamps and user IDs. For participants, running `list_contacts` or using `create_contact` allows your agent to maintain a validated list of people who can sign.

Setup guide

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

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

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

The agent uses the `list_audit_trail` tool. Because this output is validated by Pydantic, you can trust that the history records—dates, actions, users—are perfectly structured for your application.

The `get_profile` tool retrieves account profile details. Since this is a Pydantic flow, the agent will receive strongly typed fields for every piece of profile data it needs.

You call `list_signature_requests`. The result is immediately passed through validation, ensuring that the returned list of request IDs and statuses are always in the expected format.

Use `list_signers` to get a definitive list of participants for any request. The Pydantic validation confirms that the role and identity fields are present and correctly typed.

The agent calls `get_document` to fetch file metadata. This action is guaranteed to return a structured object, making downstream processing reliable.

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