How to Use the TextGrid MCP in LangChain

Q: How does TextGrid help with LangChain for message tracking?

LangChain can build a multi-step process. You run listsmsmessages to get the history, and then pass that list into the next step of your chain. The agent uses that data to determine what actionable summary needs to be sent back.

Q: What if I want to check billing data in my LangChain agents?

You can easily incorporate usage tracking. The agent calls getusagestatistics early in the chain. This result acts as a decision point, allowing subsequent steps to halt or proceed based on cost limits.

Q: Does TextGrid allow me to manage my account details using LangChain?

Yes. You'll start by calling getaccountdetails. The agent then treats the returned data—like balance or profile info—as a critical input for deciding if another tool, like sending an SMS, can be called.

Build multi-step logic with LangChain and the TextGrid MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TextGrid MCP to LangChain

Create your Vinkius account to connect TextGrid 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 TextGrid with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Sequential Messaging Workflows

Design a chain where the agent first checks `get_account_details` to confirm the balance, then uses that result to decide whether calling `send_sms_message` is appropriate. This ensures your multi-step reasoning doesn't fail due to simple billing issues. You can build complex decision trees: if the initial check fails, the agent pivots and calls `get_usage_statistics` instead of failing outright. It’s all about controlling the flow between tool outputs.

Voice Call Orchestration

The LangChain framework makes managing voice complicated. You can chain together a sequence: first, calling `search_available_numbers` to find a number, then using that result immediately to execute `initiate_voice_call`. The output of the search dictates the next action. This isn't just running tools in parallel; it's making sure step two *needs* the specific data found in step one. It’s crucial for reliable call setup.

API Key Lifecycle Management

Need to manage credentials as part of a larger process? An agent can first use `list_api_keys` to verify which keys exist, and then call another function that might trigger an update or removal. This makes credential management part of the operational logic. It gives you full observability into your system's setup. You don't just list keys; the chain decides what to do with that list based on external conditions.

Setup guide

Set up TextGrid 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 TextGrid 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({
    "textgrid-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 TextGrid 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 TextGrid. 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 TextGrid 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 TextGrid MCP in LangChain

LangChain can build a multi-step process. You run `list_sms_messages` to get the history, and then pass that list into the next step of your chain. The agent uses that data to determine what actionable summary needs to be sent back.

Absolutely. You can structure a sequence: first, the agent searches for a number using `search_available_numbers`, and then that returned number ID is immediately passed to `initiate_voice_call`. It keeps your multi-step process grounded.

You can easily incorporate usage tracking. The agent calls `get_usage_statistics` early in the chain. This result acts as a decision point, allowing subsequent steps to halt or proceed based on cost limits.

Yes. You'll start by calling `get_account_details`. The agent then treats the returned data—like balance or profile info—as a critical input for deciding if another tool, like sending an SMS, can be called.

The server primarily handles billing and message metadata. Specific data types include account balance (from `get_account_details`), usage records (from `get_usage_statistics`), and SMS/MMS content details.

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