How to Use the Descript MCP in LangChain

Q: Can LangChain trace my Descript API calls?

Yes, every tool invocation like createtranscription or createexport is fully visible inside LangSmith. You can inspect the exact inputs, outputs, and latency of your media workflows.

Q: How does LangChain handle multiple Descript projects at once?

Your agent uses listprojects to gather all active sessions and loops through them in a single execution chain. It maintains stateless calls unless you spin up a persistent session for complex multi-project edits.

Run multi-step Descript editing and transcription pipelines directly inside your LangChain agent chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Descript MCP to LangChain

Create your Vinkius account to connect Descript 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 Descript with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Descript MCP Server Tools for Automated Audio Pipelines

The Descript MCP Server lets your LangChain agents trigger transcription jobs using `create_transcription` as a direct step in your pipeline. Your agent takes raw media URLs from previous steps, kicks off the transcription, and waits for the output. Once the file is processed, the agent grabs the text using `get_transcription` and feeds it directly into your LLM chain. This workflow runs entirely via code, eliminating manual uploads and human handoffs in your media processing runs.

Multi-Step Project Export Pipelines

You can configure LangChain agents to manage Descript projects over MCP by querying `list_projects` and fetching specific assets. When a video edit is approved, the agent fires `create_export` to render the final cut. The agent monitors the export status using `list_exports` before passing the final video link to downstream LangChain tools. You track the latency and token usage of each API call inside LangSmith to keep your production runs fast.

Template-Driven Project Generation

Your LangChain agent can read your active team assets using this MCP Server by running `list_drives` and `list_templates` to find the exact layout you need. It uses these templates to set up new editing workspaces without human intervention. By querying `get_project`, the agent checks if the workspace matches your brand guidelines before writing any code. You get a deterministic setup process that handles video metadata inside your custom Python backend.

Setup guide

Set up Descript 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 Descript 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({
    "descript-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 Descript 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 Descript. 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 Descript 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 Descript MCP in LangChain

Use the MultiServerMCPClient to connect to the Vinkius endpoint and call client.get_tools(). You then pass these tools directly into your create_agent call to let your agent manage video assets.

Yes, every tool invocation like create_transcription or create_export is fully visible inside LangSmith. You can inspect the exact inputs, outputs, and latency of your media workflows.

Your agent uses list_projects to gather all active sessions and loops through them in a single execution chain. It maintains stateless calls unless you spin up a persistent session for complex multi-project edits.

Install langchain-mcp-adapters and langgraph via pip to bridge the protocol. This setup lets you run complex ReAct loops that decide when to call get_project based on previous chain outputs.

Your media files and transcriptions stay protected within the secure, ephemeral V8 isolate sandbox hosted by Vinkius. No raw video files or transcript data are stored permanently on our servers, ensuring your intellectual property remains private.

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