How to Use the Pushbullet MCP in LangChain

Q: Can LangChain automate multi-device clipboard syncing using Pushbullet?

Yes, you can build a chain that calls listrecentpushes to grab the latest clipboard item and routes it to other targets. Use sendpushnotification to distribute the text to your registered hardware.

Q: What is the best way to manage contacts and friends in LangChain?

Use the listpushcontacts tool to let your agent look up specific people before sending a push. This keeps your agent from guessing email addresses or sending notifications to invalid targets.

Get your LangChain agents pushing links, text, and files across your hardware instantly with the Pushbullet integration.

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 LangChain

Create your Vinkius account to connect Pushbullet to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain Multi-Device Routing

This MCP Server exposes the `send_push_notification` tool so your LangChain chains can route data directly to your phone or desktop. First, the agent runs `test_pushbullet_auth` to confirm your API token is active before running any multi-step pipelines. If the credentials check out, it proceeds to dispatch files or links based on your active workflow inputs. LangSmith traces every step of this execution, showing you the exact payload sent to your target screens. You can hook this tool up to your custom document processors to send summary alerts the second a long PDF finishes analysis.

Dynamic Hardware Targeting

The `list_connected_devices` tool retrieves active hardware targets so your ReAct agent knows where to route alerts. Instead of hardcoding device IDs, your pipeline checks the live list and filters for active phones or laptops. You can also run `register_new_device` to dynamically add ephemeral terminal endpoints on the fly. This approach prevents dead-end notifications when your hardware configuration changes. Combined with LangChain's multi-server MCP client, you can coordinate these hardware checks alongside database lookups in a single, unified execution graph.

Automated Channel Feed Control

Managing broadcast feeds becomes programmatic through the `subscribe_to_channel` and `unsubscribe_from_channel` tools. Your agent monitors incoming data streams, then decides to follow or drop specific feeds based on real-time relevance scores. It reads active subscriptions via `list_channel_subscriptions` to avoid duplicate requests. These tools fit into standard LangGraph state machines that handle long-running background tasks. If a channel starts posting irrelevant noise, the agent automatically drops it without requiring you to write custom API wrappers.

Setup guide

Set up Pushbullet MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Pushbullet tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "pushbullet-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Pushbullet transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Instantiate the MultiServerMCPClient pointing to the server URL, then call get_tools to pull the tools. Pass those directly to your helper agent constructor. You can track latency and payload sizes inside your LangSmith dashboard.

Yes, you can build a chain that calls `list_recent_pushes` to grab the latest clipboard item and routes it to other targets. Use `send_push_notification` to distribute the text to your registered hardware.

The server returns raw API errors directly to your chain if you hit Pushbullet limits. You can monitor connection health by calling `get_api_status` inside your chain's error-handling loops.

Use the `list_push_contacts` tool to let your agent look up specific people before sending a push. This keeps your agent from guessing email addresses or sending notifications to invalid targets.

Your push history, contact emails, and device IDs pass through a secure local MCP sandbox before hitting Pushbullet. We never log or store your clipboard payloads or API tokens on our platform.

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