How to Use the Knackly MCP in AutoGen

Q: How do I configure Knackly for my AutoGen agents?

Install autogen-extmcp and use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting tool list directly to your AssistantAgent constructor.

Q: Can multiple AutoGen agents use Knackly at the same time?

Yes. One agent can run getrecorddetails to audit a past entry while another prepares to draft a new one. They share the same MCP tool access but apply different instructions.

Q: Can the agents read the final document text?

The tools provide metadata about the files via listgenerateddocuments and the inputs via listdatarecords. They do not extract the raw PDF text itself.

Deploy debating AutoGen agents to validate and generate your Knackly legal documents automatically.

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 AutoGen

Create your Vinkius account to connect Knackly to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Template Validation

Knackly integrates into AutoGen so different agents can debate the correct way to fill out a contract. A legal-reviewer agent pulls the template structure using `list_data_models` while a data-entry agent proposes the variables. They fight over the inputs. If the legal agent spots a missing conditional field for a specific jurisdiction, it rejects the proposal. Only when both agents reach a consensus does the system finally execute `create_data_record`.

Audit Workspaces via MCP Server

You can assign an auditor agent to continuously monitor your environments. This agent runs `list_workspaces` and `list_catalogs` to map out exactly where your business forms live. If another agent needs to generate a document, it asks the auditor for the correct destination. The auditor checks the active catalogs and provides the exact IDs required, preventing misfiled records across your organization.

Verify Generation and Webhooks

The job isn't done just because a record exists. A QA agent steps in and calls `list_generated_documents` to confirm the file actually compiled correctly. Meanwhile, an ops agent might run `list_webhooks` to ensure the downstream delivery systems are listening. If the webhook is missing, the agents coordinate a fallback plan and notify the user before closing the session.

Setup guide

Set up Knackly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Knackly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Knackly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Knackly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Knackly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Knackly data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with a `StreamableHttpServerParams` configuration. Pass the resulting tool list directly to your `AssistantAgent` constructor.

Yes. One agent can run `get_record_details` to audit a past entry while another prepares to draft a new one. They share the same MCP tool access but apply different instructions.

If a tool call fails, the agent reads the error message and attempts to correct the payload. It will actively debug its own parameters before trying to create the record again.

The tools provide metadata about the files via `list_generated_documents` and the inputs via `list_data_records`. They do not extract the raw PDF text itself.

Your client data and contract variables never touch persistent storage on our end. The Vinkius infrastructure routes the MCP Server payloads directly to the provider through a secure, stateless tunnel that drops the connection the second the transaction completes.

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