How to Use the Keepcon MCP in Google ADK

Q: Can I limit which Keepcon tools my Gemini agent sees?

Absolutely. You use the toolnames filter in the ADK setup. This allows you to expose moderatecontent to a frontline agent while restricting searchprofiles to an admin bot.

Q: What happens if a batch import fails?

The importbatch tool returns an error instead of an import ID. Your agent catches this and retries the payload or escalates the failure to an operations channel.

Q: How do I map Twitter users to Keepcon via Google ADK?

Prompt your agent to use the getprofilebysocialid tool. It accepts the network name and the specific user ID, returning the canonical Keepcon profile record.

Q: What is the data privacy model for Keepcon batch exports?

Batch records pulled via exportresults contain sensitive user generated content and moderation tags. The MCP architecture ensures these payloads transit through a zero-trust, ephemeral sandbox. Vinkius never logs the contents of the exported arrays.

Connect Keepcon to the Google ADK and let Gemini agents moderate enterprise content.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keepcon MCP to Google ADK

Create your Vinkius account to connect Keepcon 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 Keepcon with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-aware profile investigations.

The Keepcon MCP Server gives Gemini agents direct access to your moderation user base. By calling `search_profiles`, the agent filters through historical offenders and retrieves their metadata. Gemini models hold over a million tokens in context. You instruct the agent to run `list_profiles`, dump hundreds of user histories into the prompt, and ask Vertex AI to identify coordinated spam rings across your platform.

Bulk moderation pipelines.

Enterprise workloads require asynchronous data handling. The agent triggers `import_batch` to push a massive dataset of user comments into the Keepcon semantic engine. After the analysis completes, the agent uses `export_results` to retrieve the batch decisions. It finalizes the job with `acknowledge_results`. You easily pipe these exported decisions straight into a BigQuery table for your analytics team.

Real-time decision routing.

Live chat and support forums need instant verdicts. The agent intercepts a message and fires `moderate_content` to get an immediate approve or reject signal along with specific violation tags. If a legitimate user gets flagged, the agent issues a `submit_feedback` call to correct the false positive. This trains the underlying Keepcon engine, ensuring your Google Cloud deployment adapts to your specific community guidelines over time.

Setup guide

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

Install google-adk and wrap your endpoint URL in StreamableHttpServerParameters. Pass that into McpToolset and assign it to your LlmAgent tools array.

Absolutely. You use the tool_names filter in the ADK setup. This allows you to expose `moderate_content` to a frontline agent while restricting `search_profiles` to an admin bot.

The `import_batch` tool returns an error instead of an import ID. Your agent catches this and retries the payload or escalates the failure to an operations channel.

Prompt your agent to use the `get_profile_by_social_id` tool. It accepts the network name and the specific user ID, returning the canonical Keepcon profile record.

Batch records pulled via `export_results` contain sensitive user generated content and moderation tags. The MCP architecture ensures these payloads transit through a zero-trust, ephemeral sandbox. Vinkius never logs the contents of the exported arrays.

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