How to Use the Thoughtly MCP in LangChain

Q: Can I view my Thoughtly account info through LangChain?

Your agent can pull your profile data using getuser. This is useful if your chain needs to verify account limits or caller IDs before running a massive batch of outbound dials.

Build automated voice outreach pipelines. Connect Thoughtly to LangChain and let your agents dial, log, and sync contacts autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Thoughtly MCP to LangChain

Create your Vinkius account to connect Thoughtly 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 Thoughtly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

LangChain MCP Server Integration

LangChain agents excel at multi-step reasoning. Give them the Thoughtly MCP Server, and they can manage your entire address book without human oversight. Your agent checks your database and fires off a `create_contact` request if a lead is missing. From there, the chain can pull the full directory using `list_contacts`. If a user changes their email during a chat, the agent updates the record via `update_contact` before moving to the next node in your pipeline.

Autonomous Voice Outreach

Stop writing custom integration code for telephony. Your ReAct agent decides who needs a call and executes `trigger_call` directly. It passes the necessary parameters, initiating an outbound dial instantly. You can also configure chains to inspect your available voice agents. The pipeline fetches the active roster using `list_interviews`. If it needs specifics on a particular bot's configuration, it hits `get_interview` to grab those details before dialing.

Call Log Tracing and Review

LangSmith gives you full observability into your chain's execution, but you also need to know what happened on the actual phone lines. Your application can pull the entire log of past conversations via `list_calls`. For deeper analysis, the agent isolates a specific interaction and runs `get_call_history`. This feeds the raw transcript back into your LangChain workflow, letting a summary node process the text and decide the next best action.

Setup guide

Set up Thoughtly 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 Thoughtly 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({
    "thoughtly-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 Thoughtly 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 Thoughtly. 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 Thoughtly 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 Thoughtly MCP in LangChain

Install the langchain-mcp-adapters package. Initialize a MultiServerMCPClient pointing to your endpoint URL, then pass the output of client.get_tools() to your agent constructor.

Yes. If your chain's logic determines a lead is dead, it can execute `delete_contact`. Just ensure your agent prompts have strict guardrails before allowing destructive actions.

The tools themselves are stateless. You manage context by passing the output of a `get_contact` query into your LangGraph state or session memory.

Your agent can pull your profile data using `get_user`. This is useful if your chain needs to verify account limits or caller IDs before running a massive batch of outbound dials.

Audio transcripts and phone numbers pass strictly between your LangChain runtime and the API endpoint. Vinkius runs the integration in an isolated V8 sandbox that spins down immediately after execution, leaving no persistent cache of your PII.

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