How to Use the Plaud MCP in LangChain

Q: How do I install the Plaud MCP Server for LangChain?

Run pip install langchain-mcp-adapters langgraph first. Then configure a MultiServerMCPClient with your Plaud endpoint. Call client.gettools() and pass the array to your ReAct agent.

Q: Can LangChain agents read my Plaud summaries?

Yes. The agent calls getsummary to pull the AI-generated notes. You can then pass those notes into a vector store or another LLM for further processing.

Q: Does the Plaud LangChain integration support file deletion?

It does. The deletefile tool handles removal. You should probably put a human-in-the-loop approval step in your chain before letting the agent wipe recordings.

Q: How do I get the actual MP3 files?

Use the getdownloadurl tool. It returns a direct link to the audio file so your script can download it locally.

Build complex audio processing pipelines by connecting Plaud to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plaud MCP to LangChain

Create your Vinkius account to connect Plaud 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 Plaud with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Plaud Transcripts in LangChain

You don't just pull text. LangChain agents use `list_files` to find recent meetings, then pipe the IDs directly into `get_transcript`. The output from that MCP Server tool becomes the immediate input for your next chain. Maybe you want to run custom extraction. Your agent grabs the raw text, ignores the default `get_summary` output, and feeds the entire conversation into a custom prompt template. You watch the whole execution path via LangSmith tracing.

Automate Audio Archival Workflows

Storage gets messy fast. You can build a ReAct agent that scans for old files using `list_folders` and checks their metadata with `get_file_detail`. If a file meets your criteria, the agent decides what to do next. It might pull the MP3 via `get_download_url` to back it up somewhere else, then call `delete_file` to clear space. The agent makes the call based on the logic you define in your graph using this MCP Server.

Batch Tagging and Organization

Organizing hundreds of recordings manually is a massive waste of time. Your agent pulls existing taxonomies with `list_tags` and applies them to untagged files using `update_file`. Because LangChain handles state through `client.session()`, your agent remembers which files it already processed. It just works through the backlog without repeating itself.

Setup guide

Set up Plaud 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 Plaud 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({
    "plaud-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 Plaud 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 Plaud. 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 Plaud 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 Plaud MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph` first. Then configure a `MultiServerMCPClient` with your Plaud endpoint. Call `client.get_tools()` and pass the array to your ReAct agent.

Yes. The agent calls `get_summary` to pull the AI-generated notes. You can then pass those notes into a vector store or another LLM for further processing.

It does. The `delete_file` tool handles removal. You should probably put a human-in-the-loop approval step in your chain before letting the agent wipe recordings.

Use the `get_download_url` tool. It returns a direct link to the audio file so your script can download it locally.

Plaud transcripts, summaries, and MP3 links pass through an isolated V8 sandbox on Vinkius. The server operates ephemerally, meaning your voice recordings and text data disappear from memory the moment the request 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