How to Use the Knackly MCP in OpenAI Agents SDK

Q: How do I configure Knackly with the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to the mcpservers list in your Agent constructor.

Q: Can the OpenAI Agents SDK read my Knackly templates?

Yes. The agent calls listdatamodels to pull the structure of your templates. It uses this schema to understand which conditional fields it needs to fill.

Q: How does Knackly handle missing fields in the OpenAI Agents SDK?

If the agent omits a required variable, the createdatarecord payload will fail. You should configure OpenAI guardrails to validate all required legal fields before the agent attempts the API call.

Q: Does this MCP Server support async operations?

Yes. The SDK uses an async with context manager. Set cacheToolsList=True so your agent does not re-fetch the tool definitions on every turn.

Connect the Knackly MCP Server to the OpenAI Agents SDK to build production document automation pipelines.

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 OpenAI Agents SDK

Create your Vinkius account to connect Knackly to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate document generation

`create_data_record` triggers the document assembly workflow right from your OpenAI agent. You pass the conditional logic parameters, and the agent writes the new record into your system. Because you are running the OpenAI Agents SDK, you can set strict guardrails on these payloads. The agent validates the contract variables before execution, preventing bad data from generating invalid legal documents.

Navigate workspaces with this MCP Server

`list_workspaces` and `list_catalogs` let your agent discover available template repositories. Instead of hardcoding template IDs, the agent queries the live environment to find the exact legal or business catalog it needs. You can hand off tasks between specialized agents. One agent queries `list_data_models` to map the required fields, then passes that schema to a drafting agent that formats the final payload. Full tracing in the OpenAI dashboard shows you exactly which template the agent selected.

Monitor webhooks and generated outputs

`list_generated_documents` verifies that your document actually compiled. The agent checks the final output queue to confirm the PDF or Word file exists. If something stalls, `list_webhooks` shows you the active event listeners. Your production agent can read these configurations to ensure upstream systems will receive the completion ping when the document finishes assembling.

Setup guide

Set up Knackly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Knackly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Knackly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Knackly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Knackly Agent",
            instructions="You have access to Knackly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL and pass it to the `mcp_servers` list in your Agent constructor.

Yes. The agent calls `list_data_models` to pull the structure of your templates. It uses this schema to understand which conditional fields it needs to fill.

If the agent omits a required variable, the `create_data_record` payload will fail. You should configure OpenAI guardrails to validate all required legal fields before the agent attempts the API call.

Yes. The SDK uses an async with context manager. Set `cacheToolsList=True` so your agent does not re-fetch the tool definitions on every turn.

Vinkius runs this MCP integration inside a V8 Isolate Sandbox. Your legal contract variables and generated document metadata never persist in our infrastructure. The connection drops immediately after the payload executes.

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