How to Use the Descript MCP in LlamaIndex

Q: Can LlamaIndex query Descript project details dynamically?

Yes, your agent uses getproject to fetch metadata and updates its query engine in real-time. This allows the LLM to answer questions about video status based on live API data.

Q: Can I filter which Descript MCP tools LlamaIndex has access to?

Yes, you can use the allowedtools filter during initialization to restrict your agent's capabilities. For example, you can limit the agent to reading tasks by exposing only listprojects and gettranscription.

Index your Descript video transcripts directly into LlamaIndex vector stores for semantic search.

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 LlamaIndex

Create your Vinkius account to connect Descript to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Descript MCP Server Transcripts for RAG Search

The Descript MCP Server allows LlamaIndex to fetch raw text data using `get_transcription` and convert it into searchable vectors. Your RAG pipelines can query past videos and audio files without needing manual text exports. By calling `create_transcription` on new uploads, the system automatically feeds the fresh text into your vector database. This keeps your semantic index updated with the latest spoken content from your media library.

Semantic Search Across Video Projects

Your LlamaIndex agent scans your entire workspace over MCP by calling `list_projects` and fetching metadata for each file. It builds a structured index of your video library so you can search for key phrases across multiple drives. Once the agent locates the correct project via `get_project`, it can retrieve the exact timestamped text. This lets you pinpoint where specific topics were discussed without scrubbing through hours of footage.

Asset Selection and Template Retrieval

LlamaIndex uses `list_templates` to index your layout designs and find the right match for new video runs. The agent queries this local index to determine which template fits the content topic best. By querying `list_drives`, the agent maps out where your media is stored and updates its internal document store. You avoid hardcoding folder paths because the agent discovers the correct directory structure dynamically.

Setup guide

Set up Descript MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Descript MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Descript tools.",
)
response = await agent.run("List recent Descript data")

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 LlamaIndex

You load the tools using McpToolSpec from llama-index-tools-mcp and fetch the text via get_transcription. The agent then parses this output into document nodes for your vector index.

Yes, your agent uses get_project to fetch metadata and updates its query engine in real-time. This allows the LLM to answer questions about video status based on live API data.

Initialize the BasicMCPClient with your Vinkius endpoint, then pass it to McpToolSpec(client=mcp_client). Call to_tool_list_async() to get the executable tools for your agent.

Yes, you can use the allowed_tools filter during initialization to restrict your agent's capabilities. For example, you can limit the agent to reading tasks by exposing only list_projects and get_transcription.

No, your media metadata and transcript texts are processed inside Vinkius's isolated, zero-trust V8 sandbox. Only the text chunks you choose to index are sent to your local or cloud vector database.

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