How to Use the Glean MCP in Google ADK

Q: Can Google ADK use Glean to find internal team contact info?

Yes, the Google ADK agent calls searchpeople to look up employee profiles and department structures. This is ideal for routing alerts generated by your Google Cloud monitoring tools.

Q: How does Google ADK handle Glean rate limits during bulk indexing?

The SDK manages execution queues, but you can also use checkgleanstatus to monitor connection health. If rate limits are hit, the agent pauses further bulkindexdocuments calls.

Connect Gemini's million-token context to your Glean index using the 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 Glean MCP to Google ADK

Create your Vinkius account to connect Glean 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 Glean with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Enterprise Search via Google ADK

Gemini models excel at processing massive datasets, but they still need live Glean records. This MCP Server lets your Google ADK agents run `search` and `get_document` across all your internal wikis and drives. The agent can pull thousands of lines of Glean documentation directly into Gemini's million-token window for deep reasoning. Instead of guessing, the Google ADK agent reads actual Glean source files to draft proposals. You avoid context fragmentation by letting Gemini fetch entire Glean directories in a single pass.

Target Specific Enterprise Datasources

Narrow down your search parameters to prevent Google ADK distraction and save Gemini API quota. Your Gemini agent uses `search_by_datasource` to query specific Glean platforms like Slack or Confluence directly. If it needs structured files, it calls `list_collections` and `get_collection` to map out internal asset folders. This targeted retrieval ensures your Google ADK agent only processes highly relevant Glean data. It keeps your Google Cloud infrastructure costs down while maintaining fast response times.

Live Index Updates from BigQuery Pipelines

Bridge your Google Cloud data warehouses with your Glean search index. When BigQuery jobs complete, your Google ADK agent can call `index_document` or `bulk_index_documents` to publish the raw output. This updates your Glean index instantly, making new data searchable for everyone. If a BigQuery pipeline run fails, the Google ADK agent runs `delete_document` to remove those corrupted files from Glean. This keeps your internal knowledge base accurate without manual cleanup.

Setup guide

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

Import the MCP toolset class and pass the server's HTTP endpoint to your agent constructor. This exposes tools like `search` and `chat` to your Gemini model automatically.

Yes, the Google ADK agent calls `search_people` to look up employee profiles and department structures. This is ideal for routing alerts generated by your Google Cloud monitoring tools.

The SDK manages execution queues, but you can also use `check_glean_status` to monitor connection health. If rate limits are hit, the agent pauses further `bulk_index_documents` calls.

Vinkius hosts and manages the server in a secure sandbox, giving your Google ADK agent a single secure endpoint. You don't need to configure local firewalls or complex proxies.

The server uses ephemeral V8 isolates to run each tool call, meaning employee profiles fetched via `search_people` are never cached or leaked. Your Google Cloud environment connects via a single token, keeping your Glean credentials isolated from your Google ADK agents.

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