How to Use the DocsBot MCP in Google ADK

Q: How do I configure Google ADK to connect to the DocsBot MCP Server?

Install the library with pip install google-adk. Then, instantiate McpToolset using StreamableHttpServerParameters pointing to your Vinkius endpoint, and pass it to your LlmAgent tools array.

Q: What is the best way to handle long-context reasoning with these tools?

Use listbotknowledgesources to gather the list of training documents, then let Gemini's 1M+ token context ingest the relevant metadata. This allows the model to reason across your entire support library.

Connect DocsBot to your Google ADK pipelines to feed structured knowledge directly into long-context Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocsBot MCP to Google ADK

Create your Vinkius account to connect DocsBot 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 DocsBot with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed massive context windows with complete DocsBot knowledge

Pulling complete source lists via `list_bot_knowledge_sources` lets your agent feed Google ADK's long-context window. Gemini models shine when you feed them massive amounts of data, and using this MCP Server makes your grounding step incredibly precise. After mapping the sources, the agent can use `search_bot_sources` to pull specific files or URLs. You get highly targeted context without bloating your prompts.

Cross-reference Google ADK BigQuery data with DocsBot logs

Exposing `list_bot_interaction_logs` allows you to cross-reference user queries with Google ADK performance metrics. If you run your enterprise data on Google Cloud, you can join your BigQuery tables with DocsBot logs. Analyzing these patterns lets you identify which technical documents are failing to answer user questions. Your agent can flag these gaps by calling `get_bot_knowledge_summary` to see if a source needs updating.

Restrict tool exposure for secure enterprise deployments

Restricting tool exposure is simple when you map `ask_bot_question` to your Google ADK configuration. Security teams hate exposing unnecessary tools to LLMs, and this MCP Server allows you to apply a `tool_names` filter easily. Limiting the tools keeps your agent focused and prevents it from calling configuration tools like `get_docsbot_account_metadata`.

Setup guide

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

Install the library with `pip install google-adk`. Then, instantiate `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius endpoint, and pass it to your `LlmAgent` tools array.

Yes, your agent can retrieve the latest questions and answers using `list_bot_interaction_logs` and then run analytics queries on BigQuery. This helps you monitor how well your customer support bot is performing over time.

Yes, you can use the native tool filtering parameters in Google ADK to expose only specific tools. For instance, you can restrict the agent to `ask_bot_question` and block access to team configuration tools.

Use `list_bot_knowledge_sources` to gather the list of training documents, then let Gemini's 1M+ token context ingest the relevant metadata. This allows the model to reason across your entire support library.

Your training PDFs and URLs are never cached on the Vinkius platform. All data requests through the MCP integration to `list_bot_knowledge_sources` are handled via ephemeral, zero-trust V8 isolates that instantly destroy session data upon tool completion.

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