How to Use the Toky MCP in LangChain

Q: How do I find contact information using Toky and LangChain?

You call getcontact to pull specific details about any Toky record. If the person doesn't exist, you can use listcontacts first to verify the system state.

Q: What tools does this MCP Server provide for managing calls in LangChain?

It offers getcall and listcalls. You get specific call details, or you list all recent activity using pagination parameters like limit and offset.

Q: Is it possible to create new records for Toky agents with LangChain?

While the listing includes getagent and listagents, the current tools don't include a specific creation function. You can only retrieve existing agent details.

Q: Can I list voicemails using Toky and LangChain?

Yes, you use the listvoicemails tool. This lets your workflow get an overview of all recorded messages by handling pagination.

Build multi-step communication logic and complex workflows using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Toky MCP to LangChain

Create your Vinkius account to connect Toky to LangChain 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 Toky with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage contacts with the MCP Server

The `get_contact` tool pulls specific details about a Toky contact record. You can then use `create_contact` to build out new records, or run `list_contacts` to check all existing ones in bulk. Your agent uses these tools together: it first lists contacts, determines if the target exists, and if not, calls `create_contact` before moving on.

Check call history with LangChain

Use `get_call` to pull details for a single Toky call. You can also run `list_calls` when you need an overview of recent activity, paginating through the results if necessary. This lets your ReAct agent check if a conversation was missed before deciding whether it needs to use `get_voicemail` next.

Send messages and look up agents

The `send_sms` tool allows you to dispatch texts directly through Toky. Need to know who you're texting? Call `get_agent` to retrieve agent details first. This sequence lets your LangChain workflow check the recipient's status and then execute a communication action, all in one chain.

Setup guide

Set up Toky 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 Toky 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({
    "toky-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 Toky 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 Toky. 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 Toky 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 Toky MCP in LangChain

You call `get_contact` to pull specific details about any Toky record. If the person doesn't exist, you can use `list_contacts` first to verify the system state.

It offers `get_call` and `list_calls`. You get specific call details, or you list all recent activity using pagination parameters like limit and offset.

While the listing includes `get_agent` and `list_agents`, the current tools don't include a specific creation function. You can only retrieve existing agent details.

Yes, you use the `list_voicemails` tool. This lets your workflow get an overview of all recorded messages by handling pagination.

This server handles core communication records, including contact details, call logs, agent information, and voicemail transcripts.

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