How to Use the Docupilot MCP in Pydantic AI

Q: Can I list templates from Docupilot in Pydantic AI?

Yes. The listdocupilottemplates tool returns the template data. You can then parse this using your defined Pydantic models for type-safe handling.

Q: Where do I find recent merges in Pydantic AI?

Call listlatestdocumentmerges. It provides an ordered list of recent activity, allowing your agent to verify that a document was successfully created.

Q: Is the Docupilot account metadata accessible in Pydantic AI?

Yes, using getdocupilotaccountmetadata. The data is parsed into your models, letting you monitor your usage limits in real-time.

Ensure type-safe document workflows by connecting Pydantic AI to the Docupilot 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 Docupilot MCP to Pydantic AI

Create your Vinkius account to connect Docupilot 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 Docupilot with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe merge triggers for Pydantic AI

Every call to `trigger_document_merge` is validated against your Pydantic models. If your data structure doesn't match the template, the agent catches it before the request is sent. This prevents garbage data from hitting the template. Your agent receives a clear validation error if the schema is violated.

Schema-verified template management in Pydantic AI

Use `get_template_schema` to pull the exact fields required for your templates. Pydantic AI enforces these constraints at runtime. This makes your document logic predictable. You know exactly what fields `get_template_merge_field_audit` expects, reducing the chance of runtime failures.

Strict document auditing for Pydantic AI

Track every generated file with `list_generated_documents`. The responses are mapped to your models, ensuring consistent access to file URLs and statuses. If a merge fails, `list_failed_document_merges` provides structured error data. Your agent can then handle the failure based on the specific error code returned.

Setup guide

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

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

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

The MCP toolset defines Pydantic models for every request and response. If the Docupilot API returns unexpected data, the agent triggers a validation error immediately.

Yes. The `list_docupilot_templates` tool returns the template data. You can then parse this using your defined Pydantic models for type-safe handling.

Call `list_latest_document_merges`. It provides an ordered list of recent activity, allowing your agent to verify that a document was successfully created.

Yes, using `get_docupilot_account_metadata`. The data is parsed into your models, letting you monitor your usage limits in real-time.

You manage the connection via an authenticated endpoint. All data transfers between the server and your agent are scoped to your specific account.

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