How to Use the Knackly MCP in Pydantic AI

Q: How do I add Knackly to my Pydantic AI agent?

Install pydantic-ai-slimmcp. Define your connection using the unified MCPToolset class with your HTTP endpoint, and pass it in the toolsets array.

Q: Can Pydantic AI read specific Knackly records?

The agent uses getrecorddetails to pull the exact parameters of a past generation. It maps these details into your defined data classes for safe processing.

Connect the Knackly MCP Server to Pydantic AI for type-safe, validated document automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knackly MCP to Pydantic AI

Create your Vinkius account to connect Knackly 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 Knackly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read catalogs and models safely

`list_catalogs` and `list_data_models` return the exact structure of your document templates. The agent queries these endpoints to understand the conditional logic required for a specific legal agreement. Because you use Pydantic AI, every response from this MCP Server runs through strict runtime validation. If the API returns an unexpected field type, the framework fails loudly. Your agent will never hallucinate a template ID.

Create records with Pydantic AI

`create_data_record` pushes your validated data into the document assembly engine. The agent constructs the payload based on the template schema and fires the request. Model-agnostic design means you can swap between Claude, OpenAI, or local models for the reasoning phase. The framework ensures the final payload matches the exact types required before it ever hits the server.

Verify outputs and webhooks

`list_generated_documents` lets your agent check the output queue for finished files. It pulls the metadata to confirm the document compiled without errors. You can also monitor your event triggers using `list_webhooks`. The agent reads the webhook configurations to ensure your system will catch the completion event, keeping your automated pipeline moving.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Define your connection using the unified `MCPToolset` class with your HTTP endpoint, and pass it in the `toolsets` array.

Yes. The framework enforces strict type-checking on every payload returned by the server. If a field is missing, you get a clear validation error immediately.

The agent uses `get_record_details` to pull the exact parameters of a past generation. It maps these details into your defined data classes for safe processing.

The framework supports both Streamable HTTP and SSE transports. Use the HTTP approach with your provided endpoint token for the most direct connection.

We manage the connection using strict ephemeral sandboxing. Your client names, conditional clauses, and template structures only exist in memory during the request and vanish the second the transaction closes.

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