How to Use the GetStream MCP in LlamaIndex

Q: Can LlamaIndex update GetStream activities?

Yes. Your FunctionAgent can call updateactivities to modify existing timeline posts based on user prompts. The changes reflect immediately in the API.

Q: How does LlamaIndex handle GetStream pagination?

You configure your data loaders to loop through getfeed using the returned cursors. The agent indexes each page of activities until the feed is fully ingested.

Q: Can I filter which GetStream tools LlamaIndex sees?

You restrict access using the allowedtools parameter. If you only want the agent reading data, you provide getfeed and block addactivitytofeed.

Index your GetStream activity feeds and follower graphs directly into LlamaIndex 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 GetStream MCP to LlamaIndex

Create your Vinkius account to connect GetStream 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 GetStream with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index GetStream MCP Server Feeds

This MCP integration lets LlamaIndex read and store GetStream activity data. Your RAG application pulls raw timeline events using `get_activities` and converts them into searchable document nodes. You query past user interactions and get answers backed by actual API data instead of guesses. You build unified knowledge bases from active social graphs. The system pulls the latest posts with `get_feed`, embedding the text and metadata into your vector store. When a user asks about trending topics, the engine searches the index and returns exact matches from the timeline.

Query Live Follower Relationships

Social context matters for semantic search. Your application maps the entire network by calling `list_feed_followers` and indexing the connections. This gives your query engine the ability to filter search results based on who follows whom. You combine this with active updates. If a user changes their network, your tools trigger `follow_feed` or `unfollow_feed` and immediately refresh the affected index nodes. The vector store always reflects the current state of your GetStream relationships.

Embed Rich Media and Open Graph Data

Text isn't the only data you need to index. Your LlamaIndex setup extracts link metadata using `get_open_graph` and adds it to your document chunks. This means external article titles and descriptions become fully searchable within your RAG pipeline. You handle custom application state through collections. The engine retrieves structured data via `get_collection_object` and embeds it alongside the timeline activities. You get a complete, queryable snapshot of your application's custom objects.

Setup guide

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

Install llama-index-tools-mcp via pip. Setup the BasicMCPClient with your endpoint URL, pass it to McpToolSpec, and call to_tool_list_async() to get your functions.

Yes. Your FunctionAgent can call `update_activities` to modify existing timeline posts based on user prompts. The changes reflect immediately in the API.

You configure your data loaders to loop through `get_feed` using the returned cursors. The agent indexes each page of activities until the feed is fully ingested.

You restrict access using the allowed_tools parameter. If you only want the agent reading data, you provide `get_feed` and block `add_activity_to_feed`.

The server handles raw user IDs, post content, and custom collection objects. The V8 Isolate Sandbox ensures that when your query engine pulls these records into memory via MCP for embedding, the connection remains ephemeral and isolated from other tenants.

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