How to Use the Knackly MCP in CrewAI

Q: How do I equip my CrewAI agents with Knackly tools?

Install crewaitools. For basic setups, pass the Vinkius URL directly into the mcps array on your Agent definition.

Q: Can I restrict which CrewAI agents access specific Knackly tools?

You can. Import MCPServerHTTP from crewai.mcp and use toolfilter. Give your researcher access to templates and your drafter access to record creation.

Q: Does the framework support polling for finished documents?

Yes. You assign an agent to run listgenerateddocuments on a schedule, or you configure your system to listen to endpoints verified by the webhook tool.

Q: How do autonomous agents handle existing records?

An analysis agent executes listdatarecords to pull historical data. It then uses getrecorddetails to extract past clauses for reference in new drafts.

Deploy autonomous legal teams in CrewAI to draft, review, and finalize documents without human intervention.

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 CrewAI

Create your Vinkius account to connect Knackly to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map requirements with CrewAI

You don't assign one MCP agent to do everything. You build a researcher agent that queries `list_workspaces` and `list_catalogs` to map out the available contract templates. That researcher then executes `list_data_models` to understand the exact variables required for a specific non-disclosure agreement. It passes this structured schema to the drafting agent via CrewAI's shared memory.

Generate records autonomously

The drafting agent takes the schema and compiles the necessary client data. It fires `create_data_record` to push the payload into the engine for processing. A moderator agent watches this process. It immediately runs `get_record_details` to verify the drafted record against the original client intake form, catching discrepancies before the final PDF renders.

Audit outputs with this MCP Server

Your final agent acts as the delivery coordinator. It uses `list_generated_documents` to pull the finished files and prepare them for email distribution. To keep the system reliable, a background agent periodically runs `list_webhooks`. It ensures the connection between your internal systems and the API remains active, preventing silent failures in your autonomous pipeline.

Setup guide

Set up Knackly MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Knackly tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Knackly Analyst",
    goal="Access and analyze Knackly data via MCP.",
    backstory="Expert analyst with direct Knackly access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Knackly transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Knackly Analyst",
        goal="Access and analyze Knackly data via MCP.",
        backstory="Expert analyst with direct Knackly access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Knackly transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Install `crewai[tools]`. For basic setups, pass the Vinkius URL directly into the `mcps` array on your Agent definition.

You can. Import `MCPServerHTTP` from `crewai.mcp` and use `tool_filter`. Give your researcher access to templates and your drafter access to record creation.

Yes. You assign an agent to run `list_generated_documents` on a schedule, or you configure your system to listen to endpoints verified by the webhook tool.

An analysis agent executes `list_data_records` to pull historical data. It then uses `get_record_details` to extract past clauses for reference in new drafts.

Vinkius never caches your data. The MCP connection operates inside a strict execution environment. Once your agent reads a legal template structure or writes a client name, the sandbox memory is wiped clean.

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