How to Use the Knackly MCP in LlamaIndex

Q: How do I add Knackly tools to LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it with McpToolSpec and pass the asynchronous tool list to your FunctionAgent.

Q: Can LlamaIndex search through my generated Knackly documents?

The agent uses listgenerateddocuments to pull the metadata for recently created files. You can then index those file references into your RAG application for quick retrieval.

Turn your Knackly templates and legal records into a searchable knowledge base with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Knackly to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Knackly MCP Server Catalogs

Knackly feeds the exact structural data your LlamaIndex application needs to understand your document repository. By running `list_catalogs` and `list_data_models`, your agent pulls the exact schemas for every legal template you own. Those schemas get indexed directly into your vector store. When a user asks which contract applies to a non-disclosure agreement in California, LlamaIndex runs a semantic search against that indexed data. It retrieves the exact model requirements without guessing.

Query Past Document Records

You can build RAG pipelines that ground their answers in actual historical business forms. Your agent uses `list_data_records` to fetch previous entries for a specific model. If a user needs to know how a specific conditional clause was filled out last quarter, the agent calls `get_record_details`. The exact variables are retrieved, indexed, and used to generate a highly accurate, context-aware response based on real company data.

Automate New Document Assembly

LlamaIndex doesn't just read data; it takes action based on the retrieved context. Once the agent finds the right template and gathers the necessary facts from your vector store, it executes `create_data_record`. The system then verifies the output by running `list_generated_documents`. You get a complete loop where historical knowledge directly drives the creation of new, accurate legal paperwork.

Setup guide

Set up Knackly MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Knackly MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Knackly tools.",
)
response = await agent.run("List recent Knackly data")

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 LlamaIndex

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it with `McpToolSpec` and pass the asynchronous tool list to your `FunctionAgent`.

The agent uses `list_generated_documents` to pull the metadata for recently created files. You can then index those file references into your RAG application for quick retrieval.

Basic scripts just push data. This framework lets you index the output of `list_workspaces` and `list_data_models` so your AI can semantically search your available templates before acting.

It queries your vector store for the template schema, which was previously fetched via the MCP Server. It maps the user's prompt to those specific fields before creating the record.

All proprietary business logic and contract conditions accessed through the endpoints are handled via ephemeral, zero-trust connections. The Vinkius architecture ensures no workspace data persists in the middleman layer after LlamaIndex completes the read operation.

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