How to Use the Fellow MCP in LlamaIndex

Q: Can LlamaIndex update a Fellow task status after a search?

Yes, you pass the completeactionitem tool to your LlamaIndex FunctionAgent. When the agent searches your index and finds a completed task in your git logs, it calls the tool to update the status in Fellow.

Q: How do I prevent LlamaIndex from indexing sensitive Fellow meetings?

You can configure the framework's allowedtools list to restrict access. By omitting tools like liststreams or limiting listnotes to specific IDs, you control exactly which meeting contents enter your vector database.

Q: Can I search for tasks assigned to a specific teammate?

Yes, you use listusers to get the correct workspace ID, then query the indexed action items. This lets you quickly see what tasks are currently assigned to any engineer on your team.

Q: Does this MCP Server expose our workspace user directory?

The listusers tool only retrieves user profiles to help your agent assign tasks. We protect this directory data using zero-trust, ephemeral execution environments where no API tokens or user records are stored on disk.

Index your Fellow meeting notes and action items into LlamaIndex vector stores using our MCP Server for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to LlamaIndex

Create your Vinkius account to connect Fellow 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 Fellow with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Workspace Notes for RAG

The `get_note` tool retrieves the exact text of your Fellow documents so LlamaIndex can parse and chunk them into your vector database. Instead of guessing what happened in past design syncs, your query engine searches this live index to ground its answers in real decisions. This workflow eliminates hallucinations by forcing the LLM to cite specific lines from your actual notes. You run semantic searches across months of planning sessions, pulling precise technical requirements directly into your local development environment.

Query Fellow Action Items in LlamaIndex

The `list_action_items` tool feeds your current task backlog directly into LlamaIndex's data ingestion pipelines. This MCP tool feeds the framework raw task data, mapping who owns what and when they are due, which lets your agent answer complex operational queries. You ask your agent which tasks are blocking the release, and it cross-references the indexed tasks with git commits. It gives you a clear, factual status update without you having to open the Fellow web app.

Map Meeting Streams to Knowledge Bases

The `list_streams` tool maps your recurring meeting series so LlamaIndex can organize your knowledge base by project thread. By structuring your documents around these streams, your agent understands the chronological progression of your architecture decisions. You query a specific stream ID to see how a feature's scope evolved over the last quarter. The framework pulls the relevant sequence of notes, providing a clean historical timeline of your team's engineering choices.

Setup guide

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

You use the McpToolSpec with the LlamaIndex framework to call `list_notes` and `get_note`. The tool outputs are loaded as Document objects, which you then chunk and index using your standard embedding pipeline.

Yes, you pass the `complete_action_item` tool to your LlamaIndex FunctionAgent. When the agent searches your index and finds a completed task in your git logs, it calls the tool to update the status in Fellow.

You can configure the framework's allowed_tools list to restrict access. By omitting tools like `list_streams` or limiting `list_notes` to specific IDs, you control exactly which meeting contents enter your vector database.

Yes, you use `list_users` to get the correct workspace ID, then query the indexed action items. This lets you quickly see what tasks are currently assigned to any engineer on your team.

The `list_users` tool only retrieves user profiles to help your agent assign tasks. We protect this directory data using zero-trust, ephemeral execution environments where no API tokens or user records are stored on disk.

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