How to Use the Mention MCP in Google ADK

Q: Can Gemini models in the Google ADK write data back to Mention?

Yes, your agent can perform write actions like markmentionasread or favoritemention if you expose those tools. You can configure the McpToolset with a strict tool filter to prevent the model from executing write operations.

Q: How does the Google ADK handle rate limits when querying Mention?

When your agent runs listrecentmentions repeatedly, the ADK manages the HTTP connection pool to prevent rate limiting. If the API returns a throttle response, the framework pauses execution to protect your integration.

Feed real-time brand tracking data from Mention directly into Google ADK agents to power enterprise-grade BigQuery analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mention MCP to Google ADK

Create your Vinkius account to connect Mention 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 Mention with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Mention Data into Google ADK Long-Context Windows

Your agent runs `get_mention_content` to pull full-text articles and social posts into the Gemini context window. The Google ADK takes advantage of Gemini's million-token capacity, allowing the model to analyze hundreds of brand discussions simultaneously. This integration lets Gemini process large volumes of text without chunking or losing context. The agent can compare multiple findings side-by-side to detect complex narrative shifts across different media channels.

Sync Brand Alerts to Enterprise Data Pipelines

The agent invokes `list_monitoring_alerts` to retrieve your active tracking configurations. The Google ADK connects this MCP toolset directly to your Vertex AI workflows, enabling automated updates to your cloud-hosted brand dashboards. If a new competitor emerges, the agent runs `create_monitoring_alert` to start tracking them instantly. The ADK handles the underlying HTTP transport, feeding the new configuration parameters directly into your enterprise pipeline.

Search Brand Keywords and Export to BigQuery

Your agent executes `search_mentions_by_keyword` to find historical discussions across the web. The Google ADK makes it easy to pipe these search results from the MCP Server directly into BigQuery tables for long-term trend analysis and SQL querying. By running `get_alert_statistics` alongside your searches, your agent can cross-reference raw volume metrics with historical sentiment. This setup gives your marketing team immediate access to cloud-scale reputation analytics.

Setup guide

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

The ADK uses StreamableHttpServerParameters to connect to the Vinkius managed endpoint. Your API credentials are encrypted and handled at the proxy level, so your Gemini models never see or leak your active tokens.

Yes, your agent can perform write actions like mark_mention_as_read or favorite_mention if you expose those tools. You can configure the McpToolset with a strict tool filter to prevent the model from executing write operations.

When your agent runs list_recent_mentions repeatedly, the ADK manages the HTTP connection pool to prevent rate limiting. If the API returns a throttle response, the framework pauses execution to protect your integration.

Your agent can query your active event configurations using list_active_webhooks. This allows the ADK to monitor your active integrations and alert your engineering team if a webhook endpoint stops responding.

All search queries, brand alerts, and raw text retrieved from search_mentions_by_keyword are processed in an isolated runtime environment. Google ADK does not train Gemini models on your retrieved brand data, and Vinkius ensures all MCP transport layers use zero-trust encryption.

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