How to Use the Grain MCP in LlamaIndex

Q: Can LlamaIndex index transcripts from Grain automatically?

Yes, your agent can call gettranscript to retrieve the timestamped text and load it into a document object. LlamaIndex then parses and indexes this text into your vector database.

Q: How does LlamaIndex handle search queries using Grain?

The agent uses the searchrecordings tool to find matching files based on your query terms. It then retrieves the relevant transcript portions to generate a precise, grounded response.

Q: Can I filter recordings by workspace members in LlamaIndex?

Yes, your agent can call listworkspacemembers to identify specific team members. It can then cross-reference this list with listrecordings to index meetings involving specific participants.

Index meeting transcripts and AI summaries directly into your LlamaIndex vector stores using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grain MCP to LlamaIndex

Create your Vinkius account to connect Grain 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 Grain with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG pipelines with LlamaIndex and Grain

Turn your meeting history into a queryable knowledge base. This MCP Server lets you feed LlamaIndex your workspace data using `list_recordings` and index the raw text retrieved from `get_transcript`. Your RAG applications will now have access to actual spoken conversations instead of relying on stale documentation. By indexing these outputs directly into your vector store, you can ask complex questions about past decisions. The agent uses `get_insights` to ground its answers in real meeting data, minimizing hallucinations.

Automate semantic search over highlights

LlamaIndex can automatically parse and index curated meeting moments. By calling `list_highlights` or `list_shared_clips`, your agent extracts key segments and metadata to build a highly targeted index. This is perfect for tracking product feedback or customer interviews. You can also use `list_tags` to structure your index. This allows your LlamaIndex query engine to filter search results by specific topics before pulling the full details with `get_recording`.

Process external videos for indexing

You are not limited to pre-recorded meetings in your workspace. Your LlamaIndex agent can use `upload_video` to send external video URLs to the processing pipeline. Once processed, the agent retrieves the text and indexes it immediately. This capability allows you to build automated ingestion pipelines for public webinars or training videos. The agent can monitor a source, upload the file, and update your vector index without manual intervention.

Setup guide

Set up Grain 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 Grain 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 Grain tools.",
)
response = await agent.run("List recent Grain 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 Grain. 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 Grain 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 Grain MCP in LlamaIndex

Install llama-index-tools-mcp and initialize the basic client. Use McpToolSpec to load the MCP Server tools and call to_tool_list_async to pass them directly to your LlamaIndex agent.

Yes, your agent can call `get_transcript` to retrieve the timestamped text and load it into a document object. LlamaIndex then parses and indexes this text into your vector database.

The agent uses the `search_recordings` tool to find matching files based on your query terms. It then retrieves the relevant transcript portions to generate a precise, grounded response.

Yes, your agent can call `list_workspace_members` to identify specific team members. It can then cross-reference this list with `list_recordings` to index meetings involving specific participants.

Yes, your meeting transcripts and user profiles are accessed securely via Vinkius. The MCP Server runs in an isolated sandbox, ensuring your private meeting data is only processed during active indexing runs.

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