How to Use the Pushbullet MCP in LlamaIndex

Q: Can LlamaIndex send query results to my phone via Pushbullet?

Absolutely. Your agent can run the sendpushnotification tool to push search results, formatted text, or raw links directly to any device ID returned by listconnecteddevices.

Q: How does the Pushbullet MCP Server handle authentication inside LlamaIndex?

Your API key is verified securely using the testpushbulletauth tool during initialization. The server manages your token locally, ensuring your agent can query endpoints without exposing raw credentials in your application logs.

Q: What tools are available to manage my device list in LlamaIndex?

You can use registernewdevice to add script-based endpoints or removedevice to prune old hardware. This lets your agent dynamically manage where it can push indexed knowledge.

Index your Pushbullet history directly into LlamaIndex vector stores for semantic search across all your devices.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Pushbullet MCP to LlamaIndex

Create your Vinkius account to connect Pushbullet 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 Pushbullet with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Push Search

The `list_recent_pushes` tool pulls your message history directly into your LlamaIndex data ingestion pipeline. Your agent indexes these text payloads and links, turning your chaotic notification history into a searchable vector database. This means you can query past links or notes using natural language instead of scrolling through old phone notifications. By mapping these outputs into document objects, you can run semantic searches across months of shared links. The agent uses `remove_push_record` to clean up the index whenever you delete a notification from your active feed.

LlamaIndex Hardware Context

This MCP Server provides the `list_connected_devices` tool to ground your RAG applications in your actual physical workspace. Before generating a response, the FunctionAgent checks which devices are online to format the output payload correctly for your specific screen size. It can also call `get_api_status` to verify that the connection to the Pushbullet network is active. This hardware context prevents the model from sending massive text files to a smartwatch or tiny mobile screen. You get a smarter retrieval loop that knows exactly where its answers are going to be displayed.

Contextual Channel Ingestion

The `list_channel_subscriptions` tool lets your agent index public information feeds into your local knowledge base. Your LlamaIndex pipeline can automatically follow new topics using `subscribe_to_channel` when a user asks about a specific theme. Once subscribed, the agent pulls the latest feed updates directly into your vector store. It can also clean up stale feeds by calling `unsubscribe_from_channel` to keep your index lean and relevant.

Setup guide

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

Load the tools using McpToolSpec and pass them to your FunctionAgent. Call `list_recent_pushes` to fetch your notification logs, then convert those text blocks into vector embeddings for semantic search.

Absolutely. Your agent can run the `send_push_notification` tool to push search results, formatted text, or raw links directly to any device ID returned by `list_connected_devices`.

Your API key is verified securely using the `test_pushbullet_auth` tool during initialization. The server manages your token locally, ensuring your agent can query endpoints without exposing raw credentials in your application logs.

You can use `register_new_device` to add script-based endpoints or `remove_device` to prune old hardware. This lets your agent dynamically manage where it can push indexed knowledge.

All notification payloads, device lists, and subscription data are handled inside an ephemeral, zero-trust MCP environment. Your sensitive data goes straight to Pushbullet's API without being cached or inspected by outside servers.

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