How to Use the Messenger MCP in Google ADK

Q: How do I connect the Messenger MCP Server to my Google ADK agent?

Install google-adk and configure McpToolset with your Vinkius HTTP endpoint. Pass this toolset directly to your LlmAgent initialization to expose the Facebook tools to Gemini.

Q: Can Gemini use Google ADK to filter specific Messenger tools?

Yes, you can use the toolnames filter in the ADK toolset configuration. This lets you restrict your agent to read-only tools like listconversations while blocking write tools like sendmessage.

Q: Can I track which Facebook Page my agent is connected to?

Yes, running getpageinfo returns the page name and ID. Your agent uses this to confirm it is targeting the correct audience before executing any public-facing tasks.

Run your Facebook Page inbox directly from Gemini using Google ADK and the Messenger MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Messenger MCP to Google ADK

Create your Vinkius account to connect Messenger to Google ADK 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 Messenger with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Entire Messenger Histories with Google ADK

`get_messages` pulls extensive message logs directly into Gemini's massive context window. This allows your Google ADK agent to process years of customer history in a single turn. By pairing this history with `list_conversations`, the agent identifies unresolved tickets across your entire inbox. It maps out customer trends using your existing BigQuery datasets to prioritize high-value leads.

Audit Facebook Page Configurations on Google Cloud

`get_page_settings` reads your active Facebook Page rules and restrictions directly. Your Google ADK agent parses this data to ensure all automated replies comply with local page policies. Running `get_page_info` pulls the core identity details of your connected page. This MCP Server ensures your Vertex AI models always know which brand identity they are representing before drafting a reply.

Send Brand-Approved Messenger Replies via Google ADK

`list_message_creative` retrieves all pre-configured marketing assets and message templates from your page. Your agent selects the correct creative asset based on the customer's purchase history. Once the asset is selected, `send_message` fires the response directly to the customer. This gives your Google ADK agent a direct path from cloud-hosted customer data to a live chat reply.

Setup guide

Set up Messenger MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Messenger tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Messenger_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Messenger tools via MCP.",
    tools=mcp_tools,
)

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 Messenger. 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 Messenger 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 Messenger MCP in Google ADK

Install `google-adk` and configure `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset directly to your `LlmAgent` initialization to expose the Facebook tools to Gemini.

Yes, you can use the `tool_names` filter in the ADK toolset configuration. This lets you restrict your agent to read-only tools like `list_conversations` while blocking write tools like `send_message`.

Gemini leverages its million-token context window to ingest entire threads returned by `get_messages`. The ADK feeds this raw conversation data directly into the model without needing external vector databases.

Yes, running `get_page_info` returns the page name and ID. Your agent uses this to confirm it is targeting the correct audience before executing any public-facing tasks.

Your Facebook Page messages and settings are processed in an ephemeral, zero-trust sandbox. The transport layer uses end-to-end encryption, ensuring your chat data never leaks into public training sets.

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