How to Use the Bland AI MCP in LangChain

Q: Are Bland AI logs available inside LangChain?

You access logs by calling listcalls through the adapter. This brings the data directly into your agent's context for analysis.

Build complex voice workflows in LangChain by chaining Bland AI phone operations into your multi-step reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bland AI MCP to LangChain

Create your Vinkius account to connect Bland AI 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 Bland AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Bland AI calls in LangChain

Feed your agent the ability to trigger `send_call` and `send_batch` directly within a sequential chain. Your agent evaluates the results of each step to decide which phone operation happens next. This setup connects your logic to live telecom events. Use the output of `analyze_call` to determine the next link in your chain, letting the agent adjust its strategy based on real-time feedback.

Manage telecom state with LangChain

Keep track of your infrastructure by using `list_inbound` and `list_calls` inside your agent's memory. It sees every number you own and every interaction that just finished. Every tool call registers in your LangSmith trace. You get a clear view of latency and token usage for every interaction with this MCP Server.

Control live sessions via LangChain

Inject `end_call` into your error-handling logic to stop problematic calls instantly. It gives your agent the power to kill a connection if the conversation goes sideways. Use `get_recording` to pull raw audio files into your pipeline for further processing. Your agent handles the entire lifecycle of the phone call without leaving your code base.

Setup guide

Set up Bland AI 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 Bland AI 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({
    "bland-ai-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 Bland AI 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 Bland AI. 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 Bland AI 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 Bland AI MCP in LangChain

You pass the tool definitions to your agent and invoke them within a chain. The agent selects the correct function when the logic dictates, such as calling `send_call` with a specific number.

Yes, you build pipelines where the agent decides the order of operations. It might query `get_call_details` first to inform the next `send_call` command.

You access logs by calling `list_calls` through the adapter. This brings the data directly into your agent's context for analysis.

The server is stateless by default. Use the client session feature if you need to maintain context across multiple turns.

Your call transcripts and audio files remain isolated within your infrastructure. The connection uses an endpoint token to ensure only your agent accesses sensitive call variables.

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