How to Use the Deepgram MCP in LangChain

Q: Can LangChain agents transcribe Deepgram audio autonomously?

They do it out of the box. Giving your agent the transcribeurl tool lets it handle the API call and parse the text directly into its scratchpad.

Q: How do I track Deepgram usage in LangChain?

Call getusage inside your chain. Those results appear in your LangSmith traces alongside standard LLM metrics.

Build multi-step audio processing pipelines with Deepgram tools in LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to LangChain

Create your Vinkius account to connect Deepgram 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 Deepgram with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain audio transcriptions directly

ReAct agents need fast inputs to make decisions. Dropping an audio URL into `transcribe_url` returns text instantly. That output tells your system what to execute next. Then it talks back. Passing that generated response into `speak_text` creates lifelike audio. This entire cycle runs as a single LangChain pipeline.

Manage Deepgram MCP Server access

Hardcoding API keys is a fast way to get compromised. Your multi-agent setup can provision temporary access using `create_key` for specific tasks. Once the run finishes, the system cleans up after itself. Running `list_keys` lets your admin bot audit current permissions. Spotting an anomaly triggers `delete_key` to revoke access immediately.

Track LangChain token and audio costs

Processing heavy audio pipelines burns through credits quickly. Hooking up `get_usage` lets your LangSmith traces correlate LLM token spend with transcription minutes. Before kicking off a massive batch job, the agent checks `get_balances`. Low funds will halt the chain and alert your team instead of failing halfway through the Deepgram MCP Server run.

Setup guide

Set up Deepgram 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 Deepgram 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({
    "deepgram-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 Deepgram 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 Deepgram. 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 Deepgram 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 Deepgram MCP in LangChain

Install the langchain-mcp-adapters package. Passing your endpoint to MultiServerMCPClient makes the tools available to your agent.

They do it out of the box. Giving your agent the transcribe_url tool lets it handle the API call and parse the text directly into its scratchpad.

Standardizing on this protocol means your system discovers the tools dynamically. Skipping custom wrapper functions saves hours of boilerplate coding.

Call get_usage inside your chain. Those results appear in your LangSmith traces alongside standard LLM metrics.

Vinkius runs this integration inside an isolated V8 sandbox. Pulling balances and processing voice files happens through ephemeral connections that vanish when the chain finishes.

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