How to Use the Gem MCP in Google ADK

Q: How does Google ADK connect to the Gem MCP server?

You instantiate an McpToolset with your Vinkius server URL. Then you pass that toolset into your LlmAgent's tools list. Google ADK handles the tool discovery and execution from there.

Q: Can I use Gemini's long context to find candidates in Gem with Google ADK?

Absolutely. You can have your Google ADK agent call listcandidates, feed the entire list into a Gemini 1.5 Pro model, and ask it to find profiles matching very specific, nuanced criteria. This goes way beyond simple keyword searching.

Q: How do I prevent my Google ADK agent from using certain Gem tools?

When you create the McpToolset, you can pass an optional toolnames filter. Just provide a list of the tool names you want to expose, like 'getcandidatedetails', 'listcandidates', and the agent won't see or be able to use any others.

Connect Google ADK to your Gem MCP Server for long-context analysis of your entire recruiting pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gem MCP to Google ADK

Create your Vinkius account to connect Gem 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 Gem with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Your Full Talent Pool

Your Gemini-powered agent can now reason over your entire Gem candidate database. Use `list_candidates` to pull thousands of profiles, and feed them into a long-context model. The agent can then identify candidates who match complex criteria that a simple database query would miss. Combine this with your own data in BigQuery. For example, your agent could pull a project list with `list_talent_projects` from Gem, find corresponding project data in a BigQuery table, and then generate a report on recruiter workload versus project priority.

Build Enterprise Recruiting Workflows

This isn't just for analysis; your Google ADK agent can take action. It can add new prospects with `create_crm_candidate` or log detailed notes from an interview debrief using `add_candidate_note`. You can build a system that listens to a Google Pub/Sub topic for new applicants and automatically adds them to Gem. The agent also manages existing records. It can call `get_candidate_details` to check a profile, then use `update_crm_candidate` to move them to a new stage. Because it's integrated with Google Cloud, you can trigger these actions from a Cloud Function or a Vertex AI Pipeline.

Use Your Team's Custom Fields with Google ADK

The Gem MCP server lets your agent understand your team's specific process. It calls `list_crm_custom_fields` to learn what fields you use to tag candidates, like "Visa Sponsorship Required." This lets your Gemini agent make much smarter, context-aware decisions without you hardcoding business logic. This is how you build truly intelligent automation. An agent could see a candidate has the "Executive" tag, and decide *not* to add them to a generic sequence it found with `list_outreach_sequences`. Instead, it could flag the profile for manual review by someone on the `list_recruiting_team`.

Setup guide

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

You instantiate an `McpToolset` with your Vinkius server URL. Then you pass that toolset into your `LlmAgent`'s `tools` list. Google ADK handles the tool discovery and execution from there.

Absolutely. You can have your Google ADK agent call `list_candidates`, feed the entire list into a Gemini 1.5 Pro model, and ask it to find profiles matching very specific, nuanced criteria. This goes way beyond simple keyword searching.

When you create the `McpToolset`, you can pass an optional `tool_names` filter. Just provide a list of the tool names you want to expose, like `['get_candidate_details', 'list_candidates']`, and the agent won't see or be able to use any others.

Yes, it's a perfect fit. You can deploy a Google ADK agent as a Cloud Function. For example, you could have an HTTP trigger that receives a candidate email, and the agent uses `create_crm_candidate` to add them to your Gem pipeline.

This server handles sensitive candidate information, including notes and contact details pulled via `get_candidate_details`. Your connection from Google ADK to our server is encrypted. Each transaction runs in a dedicated, memory-safe sandbox that is destroyed immediately after, ensuring your recruiting data is never persisted on our systems.

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