How to Use the ThinkStack MCP in LangChain

Q: What data types can I query about when using LangChain with ThinkStack?

You can retrieve bot configuration details via getbot, list all available actions using listactions, and get conversation context through getconversation.

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

The combination of listbots, listsources, and listactions lets you get a full picture. You can see every bot available and every piece of data it relies on.

Build Multi-Step Agents with LangChain: Connect ThinkStack tools into complex reasoning chains.

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 LangChain

Create your Vinkius account to connect ThinkStack to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Complex, Sequential Tasks

The `send_query` tool lets your agent send a query to a specific bot. Crucially, the output from that call can instantly become the input for another function—like calling `list_actions`. This ability means you build full chains of reasoning instead of just single requests. You're not limited to one step. You use this structure to make your agent decide which tools to hit and in what order, giving you deep observability across the whole process.

Audit Bot Configuration Details

Need to check how a bot works? Use `get_bot` to pull specific chatbot details. Then, if you need to see all possible actions available to it, run `list_actions`. This two-step process lets your agent fully map out the operational scope of any managed bot. It’s perfect for building reliable ReAct agents that can validate their own execution path before making a move.

Manage Source and Conversation Data

Want to track what happened? You can use `list_sources` to see the indexed knowledge base, or pull details using `get_conversation`. This gives your agent context about the data it's working with. If you need a fresh start, `delete_source` lets your client clean up old data. It’s all part of building robust, self-correcting chains.

Setup guide

Set up ThinkStack MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ThinkStack tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "thinkstack-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ThinkStack transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You map the output of one MCP Server function to the input parameter of the next. Your agent makes this decision at runtime, building a single reasoning path from multiple tools.

You can retrieve bot configuration details via `get_bot`, list all available actions using `list_actions`, and get conversation context through `get_conversation`.

The combination of `list_bots`, `list_sources`, and `list_actions` lets you get a full picture. You can see every bot available and every piece of data it relies on.

Yes, because the agent executes a chain, your tracing tools monitor the input/output for each distinct MCP Server call, allowing you to measure performance at every step.

The server touches conversation details and bot configuration. You control which specific `get_conversation` or `get_bot` calls your agent executes, maintaining a clear audit trail.

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