How to Use the ThinkStack MCP in LlamaIndex

Q: How does LlamaIndex use ThinkStack data?

LlamaIndex takes the output of MCP Server tools—like getbot results or conversation summaries—and turns them into searchable embeddings. The answer comes from this indexed knowledge, not just a function call.

Q: What kind of data sources can I add to LlamaIndex with ThinkStack?

You use addsource to crawl and index content. This includes external documents, as well as structured data retrieved via tools like listconversations.

Q: If I need to audit my setup in LlamaIndex, what tools are useful?

Use listsources to see your current index contents and checkthinkstackstatus to verify the connection health. This ensures data integrity before running a query.

Q: Can LlamaIndex handle historical conversation context?

Yes. By indexing outputs from getconversation, your system can answer questions based on past session details, making it more than just a live chatbot wrapper.

Build Knowledge-Grounded RAG Apps with LlamaIndex: Index ThinkStack data for deep semantic search results.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to LlamaIndex

Create your Vinkius account to connect ThinkStack to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ThinkStack with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Answers in Live API Data

The `add_source` tool lets you crawl and index content into a knowledge base. When your agent queries the system, the output of functions like `get_bot` or `list_conversations` gets indexed alongside documents. This means that past session data or current bot configurations become part of a unified, searchable vector store—not just memory.

Audit Bot Status and Sources

`list_sources` shows you exactly what's in your knowledge base. You can then use `check_thinkstack_status` to ensure the underlying APIs are connected before querying. This makes sure your RAG application always searches against current, verified data. It’s about making sure the index itself is reliable.

Manage and Verify Bot Assets

You can track all available bots using `list_bots` to understand your assets. Then, if you need specific details, call `get_bot`. The system also lets you manage the data it indexes with `delete_source`, keeping your knowledge base clean. This gives you fine-grained control over what information is considered 'knowledge' for retrieval.

Setup guide

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

LlamaIndex takes the output of MCP Server tools—like `get_bot` results or conversation summaries—and turns them into searchable embeddings. The answer comes from this indexed knowledge, not just a function call.

You use `add_source` to crawl and index content. This includes external documents, as well as structured data retrieved via tools like `list_conversations`.

Use `list_sources` to see your current index contents and `check_thinkstack_status` to verify the connection health. This ensures data integrity before running a query.

Yes. By indexing outputs from `get_conversation`, your system can answer questions based on past session details, making it more than just a live chatbot wrapper.

The server touches conversation details and knowledge sources. You control exactly what gets added or deleted via `add_source` and `delete_source`, giving you full visibility over your indexed data.

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