How to Use the AddSearch MCP in LlamaIndex

Q: How do I set up AddSearch with LlamaIndex?

Grab the llama-index-tools-mcp package via pip. Initialize a BasicMCPClient and wrap it with McpToolSpec to expose the tools.

Q: Can the agent filter results before embedding?

You can restrict data access using the allowedtools parameter. Just limit the agent to searchfiltered and specify the exact categories it can read.

Q: Will my LlamaIndex agent know how to sort AddSearch results?

It can use the searchsorted tool to order hits by date or relevance. This ensures the most critical information gets embedded first.

Q: How do I paginate hits in the vector store?

Pass the searchpagination tool to your FunctionAgent. It will loop through pages until it gathers enough context for the embedding process.

Turn AddSearch analytics and indexed content into a queryable vector store using LlamaIndex and this 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 AddSearch MCP to LlamaIndex

Create your Vinkius account to connect AddSearch 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 AddSearch with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Your RAG Apps in Live Search Data

Standard RAG relies on static documents. Connecting LlamaIndex to this MCP integration lets your agent pull live data using `search_keyword` and embed those results directly into your knowledge base. When users ask questions, the system checks actual site content. It avoids hallucinations by referencing the exact snippets returned from your active index.

Embed Search Analytics for Context

Knowing what customers search for provides massive context for support agents. You can pull `stats_queries` and `stats_clicks` into your vector store to track user intent over time. The agent then queries past sessions to see which search terms lead to dead ends. It uses that historical data to suggest better documentation updates.

Sync AddSearch Indexing via LlamaIndex

Keeping your site search updated usually requires custom webhooks. Your framework can monitor internal databases and fire `index_document` whenever a new article gets published. Removing old content works the exact same way. If a page gets archived, the agent automatically executes `delete_document` to keep the public search clean.

Setup guide

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

Grab the `llama-index-tools-mcp` package via pip. Initialize a `BasicMCPClient` and wrap it with `McpToolSpec` to expose the tools.

You can restrict data access using the `allowed_tools` parameter. Just limit the agent to `search_filtered` and specify the exact categories it can read.

It can use the `search_sorted` tool to order hits by date or relevance. This ensures the most critical information gets embedded first.

Pass the `search_pagination` tool to your `FunctionAgent`. It will loop through pages until it gathers enough context for the embedding process.

Vinkius routes your API keys through an ephemeral zero-trust MCP environment. Click-through analytics and site documents never persist on our infrastructure.

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