How to Use the Granola MCP in LlamaIndex

Q: How do I set up the Granola MCP Server with LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius URL. Wrap it in McpToolSpec and convert it using totoollistasync() to register the MCP tools.

Q: How does LlamaIndex organize Granola folders?

The agent calls listfolders to discover the folder structure in your workspace. It then maps this structure to index metadata, allowing you to filter vector searches by folder.

Q: Can I filter Granola documents by date in LlamaIndex?

Your pipeline uses listbydate to fetch documents from a specific timeframe. This lets you construct time-aware indexes, so your queries prioritize recent meeting decisions.

Index your Granola meeting transcripts and action items into LlamaIndex vector stores for hallucination-free RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Granola MCP to LlamaIndex

Create your Vinkius account to connect Granola 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 Granola with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structured Context Retrieval for LlamaIndex

This MCP Server provides `search_documents` to let your LlamaIndex RAG pipeline query your entire meeting history. The tool returns matching document segments that the framework indexes directly into vector storage. Instead of relying on static files, your agent pulls live data to answer questions about past decisions. This grounds your queries in actual meeting notes rather than outdated context.

Granola Document Parsing

The `get_content` tool retrieves the full structured text of any Granola meeting document for indexing. LlamaIndex parses this structured output into document nodes, preserving the original formatting for better chunking. If you need to map out who said what, the agent combines this with `get_participants` to tag nodes with speaker metadata. This metadata improves search accuracy when querying specific stakeholder statements.

Batch Note Indexing

The `get_documents_batch` tool fetches multiple meeting records in a single call to accelerate your LlamaIndex ingestion pipeline. This reduces the number of API calls when syncing a large backlog of meeting notes. Your ingestion script can use `list_recent` to identify new documents, then call the batch tool to index them incrementally. This keeps your local vector index updated with minimal overhead.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient` with your Vinkius URL. Wrap it in `McpToolSpec` and convert it using `to_tool_list_async()` to register the MCP tools.

Yes, your agent doesn't have to parse raw transcripts since it uses `get_summary` to pull pre-generated meeting overviews. This allows the indexer to store high-level overviews without processing raw transcripts.

The agent calls `list_folders` to discover the folder structure in your workspace. It then maps this structure to index metadata, allowing you to filter vector searches by folder.

Your pipeline uses `list_by_date` to fetch documents from a specific timeframe. This lets you construct time-aware indexes, so your queries prioritize recent meeting decisions.

Meeting transcripts and summaries are accessed on-demand from the Vinkius sandbox. This MCP setup ensures your raw data is never stored permanently on external servers, keeping your company syncs 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