How to Use the Deep Diff Engine MCP in LlamaIndex

Q: Does Deep Diff Engine work with the async features of LlamaIndex?

Yes, it's built for it. You can call mcptoolspec.totoollistasync() to get the tool and use it within your async LlamaIndex code. It fits right into modern Python applications without blocking.

Q: What kind of knowledge base does Deep Diff Engine help me build with LlamaIndex?

It helps you build a knowledge base about change. Instead of just indexing static documents, you're indexing the evolution of your JSON data, like configs or API schemas. This lets you ask questions about history and causality.

Index configuration history and build LlamaIndex RAG apps that can answer questions about how your JSON data has changed over time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deep Diff Engine MCP to LlamaIndex

Create your Vinkius account to connect Deep Diff Engine 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 Deep Diff Engine with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Every JSON Change

The `calculate_json_diff` tool finds the exact structural differences between two JSON objects. It returns a clean array detailing every addition, edit, and deletion, including the path to the change. You're not just getting a boolean 'is different?' answer; you're getting a detailed report. With LlamaIndex, you can automatically index these reports. Every time you compare two versions of a configuration file or an API response, the resulting diff from this MCP server gets added to your vector store. This creates a searchable history of every single modification.

Query Your Config History

Once the diffs are indexed, you can ask natural language questions about your system's history. Ask things like, 'When was the 'timeout' setting last changed in the production config?' or 'Show me all changes made to user permissions in the last week.' LlamaIndex's query engine will find the relevant diff reports from the `calculate_json_diff` tool and synthesize an answer grounded in actual data. This turns a pile of old JSON files into an intelligent, queryable knowledge base. You stop guessing and start asking.

Build Smarter RAG with LlamaIndex

This tool enhances your Retrieval-Augmented Generation (RAG) applications. When a user asks a question, LlamaIndex can retrieve not just documents, but also structured diffs that show exactly how data has evolved. The agent's answers become far more precise. Imagine asking, 'Why did the user dashboard break yesterday?' Your LlamaIndex agent can retrieve the `calculate_json_diff` output showing a change to an API response schema from that day. The answer is based on hard evidence, not a model's hallucination.

Setup guide

Set up Deep Diff Engine 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 Deep Diff Engine 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 Deep Diff Engine tools.",
)
response = await agent.run("List recent Deep Diff Engine 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 deep-diff. 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 Deep Diff Engine 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 Deep Diff Engine MCP in LlamaIndex

Add a step in your pipeline that uses Deep Diff Engine to compare the new configuration with the deployed one. Then, use LlamaIndex to index the resulting diff report with metadata like the commit hash and deploy time. This creates an auditable, searchable log of all changes.

Yes, it's built for it. You can call `mcp_tool_spec.to_tool_list_async()` to get the tool and use it within your async LlamaIndex code. It fits right into modern Python applications without blocking.

It helps you build a knowledge base about *change*. Instead of just indexing static documents, you're indexing the evolution of your JSON data, like configs or API schemas. This lets you ask questions about history and causality.

Of course. The tool returns a structured array of changes. In your LlamaIndex application, you can easily write code to inspect this array and decide whether to index the diff based on its contents, like only indexing changes to a specific sub-key.

Your JSON objects are streamed to a dedicated, zero-trust Vinkius environment for the comparison. The data is used only for the `calculate_json_diff` operation and is immediately discarded. The connection itself is authenticated via your private Vinkius token.

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