How to Use the Typefully MCP in Google ADK

Q: Can I retrieve my Typefully user profile details using the Google ADK?

Yes, you use getuserprofile. The agent retrieves your current professional information and stores it in memory alongside other long-context data. This makes sure every piece of content is written with accurate context.

Q: If I want to manage Typefully drafts, how do I use the Google ADK?

You can list drafts using listdrafts and then fetch specifics with getdraftdetails. If you need to make a change, you call updatedraft, ensuring that your changes are validated against your core data models before they ever hit the server.

Q: What does the Typefully MCP Server expose?

It exposes nine tools. These include drafting tools (createdraft, deletedraft), account management (listsocialaccounts), and publishing commands (publishimmediately, schedulecontent).

Act on your BigQuery data for Typefully publishing with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typefully MCP to Google ADK

Create your Vinkius account to connect Typefully 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 Typefully with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating Content Schedules using MCP Server

The agent can read historical engagement metrics from BigQuery, analyze the optimal posting time, and then call `schedule_content`. This links your external data directly to Typefully's publishing tools. It doesn't just write; it plans. By integrating with Google Cloud infrastructure, the agent figures out *when* you should post content based on metrics, ensuring maximum reach.

Drafting and Modifying Content via Google ADK

If your BigQuery analysis suggests a pivot in topic, the agent can generate a new draft using `create_draft`. You don't have to manually rewrite it; you just call `update_draft` on an existing asset with revised copy. This flow lets your agents perform complex reasoning—holding context across thousands of tokens—to ensure the modified content matches the strategic intent derived from large datasets.

Publishing and Account Listing via MCP Server

Before publishing, you need to verify accounts. Use `list_social_accounts` to confirm all channels are active within your Google Cloud environment. If everything checks out, the agent uses `publish_immediately` to hit the live feed. Alternatively, if you just want a quick look at what's queued up, calling `list_drafts` gives you an immediate overview of pending content.

Setup guide

Set up Typefully 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 Typefully 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="Typefully_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Typefully 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 Typefully. 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 Typefully 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 Typefully MCP in Google ADK

The Google ADK allows your agent to read data from BigQuery, determine the best action (like calling `schedule_content`), and then execute that tool against the Typefully server. It's a complete loop: Data -> Decision -> Action.

Yes, you use `get_user_profile`. The agent retrieves your current professional information and stores it in memory alongside other long-context data. This makes sure every piece of content is written with accurate context.

You can list drafts using `list_drafts` and then fetch specifics with `get_draft_details`. If you need to make a change, you call `update_draft`, ensuring that your changes are validated against your core data models before they ever hit the server.

It exposes nine tools. These include drafting tools (`create_draft`, `delete_draft`), account management (`list_social_accounts`), and publishing commands (`publish_immediately`, `schedule_content`).

This server handles user identity, draft content (textual drafts), and social account linkage information. The agent can use this structured data for complex reasoning.

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