How to Use the ChangeDetection.io MCP in LlamaIndex

Q: How does LlamaIndex handle HTML diffs from ChangeDetection.io?

The framework pulls the raw text changes using getsnapshotdiff and passes them directly to your node parser. This avoids wasting embedding tokens on unchanged site boilerplate.

Q: Can a LlamaIndex agent create new monitors on ChangeDetection.io?

Yes, your agent uses createwatch to add URLs on the fly. It can also organize them by applying tags with createtag during the same execution loop.

Q: How do I feed ChangeDetection.io history into a LlamaIndex vector store?

You query getwatchhistory through the MCP Server to pull all past versions. LlamaIndex then chunks and embeds these historical snapshots so you can search through past edits semantically.

Q: How do I avoid indexing duplicate page data?

Use getsnapshot with the "latest" keyword to only pull the most recent version of the page. This prevents your index from bloating with repetitive historical snapshots.

Feed live website changes directly into your LlamaIndex vector store using this ChangeDetection.io MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChangeDetection.io MCP to LlamaIndex

Create your Vinkius account to connect ChangeDetection.io 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 ChangeDetection.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Web Diffs into LlamaIndex

The `get_snapshot_diff` tool pulls the exact text changes between two page versions so your LlamaIndex pipeline can index only what changed. Instead of ingestion pipelines parsing entire web pages over and over, you isolate the exact diff and feed clean text updates directly into your vector store. To keep content current, your pipeline runs `get_snapshot` using the "latest" keyword whenever a watch triggers. This keeps your local indices grounded in real-time site data without pulling duplicate page headers or footers.

Automate Watch Creation from RAG Queries

The `create_watch` tool lets your LlamaIndex agent set up new monitoring targets dynamically when users ask about unindexed sources. If a user queries your index about a pricing page you don't track yet, the agent spins up a watch instantly. Grouping these new monitors immediately using `create_tag` keeps your external data sources organized inside your index. This means your knowledge base expands its own coverage footprint autonomously based on search gaps.

Query Change History with an MCP Server

The `get_watch_history` tool retrieves the full timeline of modifications for any monitored URL to build historical context for your LLM. LlamaIndex stores this chronological sequence to let you run semantic searches over how a competitor's pricing or terms changed over six months. Your agent calls `list_watches` to map out active monitors before running updates. By filtering the target list first, your pipeline avoids wasting API calls on inactive sites.

Setup guide

Set up ChangeDetection.io 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 ChangeDetection.io 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 ChangeDetection.io tools.",
)
response = await agent.run("List recent ChangeDetection.io 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 ChangeDetection.io. 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 ChangeDetection.io 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 ChangeDetection.io MCP in LlamaIndex

The framework pulls the raw text changes using `get_snapshot_diff` and passes them directly to your node parser. This avoids wasting embedding tokens on unchanged site boilerplate.

Yes, your agent uses `create_watch` to add URLs on the fly. It can also organize them by applying tags with `create_tag` during the same execution loop.

You query `get_watch_history` through the MCP Server to pull all past versions. LlamaIndex then chunks and embeds these historical snapshots so you can search through past edits semantically.

Use `get_snapshot` with the "latest" keyword to only pull the most recent version of the page. This prevents your index from bloating with repetitive historical snapshots.

Your URLs and watch configurations never leave the V8 sandbox. Vinkius secures your ChangeDetection.io API tokens in an ephemeral environment, meaning sensitive server configurations are never exposed to external LLM providers.

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