How to Use the Mastodon MCP in Google ADK

Q: How do I configure Mastodon with Google ADK?

Initialize an McpToolset using StreamableHttpServerParameters with your server URL. Pass that toolset into the LlmAgent tools array.

Q: Can Google ADK filter which Mastodon tools the agent sees?

Yes. The SDK accepts a toolnames list. You expose just search and gettagtimeline while hiding write actions like deletestatus.

Q: Does this setup support media attachments on Mastodon?

Your agent calls uploadmedia to stage the file on the instance. It uses the returned media ID to attach the file when calling poststatus.

Connect Gemini to the Fediverse using 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 Mastodon MCP to Google ADK

Create your Vinkius account to connect Mastodon 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 Mastodon with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Mastodon timelines into Google ADK

The `get_home_timeline` tool pipes raw social data straight into your agent's context window. Gemini handles millions of tokens. You dump an entire day's worth of `get_public_timeline` results into a single prompt for analysis. Enterprise setups require scale. You pull data via the MCP Server and push the structured output directly into BigQuery. The agent reads the Fedi, extracts entities, and updates your data warehouse in one pass.

Automate interactions across your instance

The `favourite_status` and `reblog_status` tools let your agent interact with community content. You configure the LlmAgent to match specific criteria. It executes the engagement actions autonomously based on your rules. It handles replies too. The agent reads context via `get_status_context`, drafts a response using Gemini, and pushes it live with `post_status`. You filter the exposed tools in your Python script to prevent accidental posts.

Map instance rules and metadata

The `get_instance_info` tool retrieves server details, contact info, and registration requirements. Your agent checks this data before attempting to create new profiles or interact with local users. It knows the environment before it acts. Compliance matters for enterprise deployments. The agent runs `get_instance_rules` to read the specific moderation guidelines of a target server. This ensures your automated actions don't violate local instance policies.

Setup guide

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

Initialize an `McpToolset` using `StreamableHttpServerParameters` with your server URL. Pass that toolset into the `LlmAgent` tools array.

Yes. The SDK accepts a `tool_names` list. You expose just `search` and `get_tag_timeline` while hiding write actions like `delete_status`.

Your agent calls `upload_media` to stage the file on the instance. It uses the returned media ID to attach the file when calling `post_status`.

You provide the instance URL and access token as environment variables. The MCP Server manages the headers and executes the requests on the agent's behalf.

The server accesses user profile metadata and direct messages. Vinkius runs the integration in a zero-trust sandbox. The connection drops when the task finishes, leaving no persistent data on the worker node.

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