How to Use the Checkr MCP in Google ADK

Q: How can my Google ADK agent get a list of all Checkr reports?

It calls the listbackgroundreports tool. Your agent gets back a list of all reports in your account, which it can then filter or summarize based on your prompt using Gemini's reasoning capabilities.

Q: How do I restrict what a Google ADK agent can do with my Checkr account?

When you configure the McpToolset for your agent, use the toolnames filter. This lets you expose only specific tools, like getreportdetails, to create an agent with read-only permissions.

Q: What's the difference between a Checkr candidate and a report?

A candidate is the person, created with createnewcandidate. A report is the result of a background check on that candidate, initiated with startbackgroundcheck and fetched with getreportdetails.

Connect your Google Cloud data to Checkr and automate background checks with 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 Checkr MCP to Google ADK

Create your Vinkius account to connect Checkr 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 Checkr with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Checks from BigQuery Events

A Gemini agent built with the Google ADK can monitor a BigQuery table of new hires. When a new row appears, the agent can automatically use the `create_new_candidate` and `start_background_check` tools to get the screening process going. This closes the loop between your data warehouse and your HR operations. You don't need to write custom glue code or use a separate integration platform. The agent handles the logic, directly connecting your source of truth in BigQuery to the Checkr API.

Build Reports with a Gemini Agent

Your agent can pull lists of reports, candidates, and invitations using `list_background_reports`, `list_checkr_candidates`, and `list_screening_invitations`. Gemini's long context window means the agent can hold all of this data in memory to answer complex questions in one shot. You could ask your agent, 'Summarize the status of all pending background checks for candidates in the Engineering department invited this month.' The agent uses the tools to get the raw data and Gemini's reasoning to synthesize the answer.

Manage Checkr from your Google Cloud MCP Server

The Google ADK lets you filter which tools are exposed to an agent. You could create a 'read-only' agent that can only use tools like `get_candidate_details` and `get_report_details` for auditing purposes. This gives you granular control over what your agents can do. For write operations, a separate, more privileged agent could handle `start_background_check`, ensuring a clear separation of concerns inside your Google Cloud project.

Setup guide

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

It calls the `list_background_reports` tool. Your agent gets back a list of all reports in your account, which it can then filter or summarize based on your prompt using Gemini's reasoning capabilities.

Yes, that's what the ADK is for. Your Gemini agent can read data from a BigQuery table or a file in Cloud Storage and use it to populate calls to Checkr tools like `create_new_candidate`.

When you configure the `McpToolset` for your agent, use the `tool_names` filter. This lets you expose only specific tools, like `get_report_details`, to create an agent with read-only permissions.

A candidate is the person, created with `create_new_candidate`. A report is the result of a background check on that candidate, initiated with `start_background_check` and fetched with `get_report_details`.

Candidate data, including names and personal identifiers, is handled by the server. Vinkius isolates every MCP Server request in a dedicated, single-use V8 sandbox. This means your data is never co-mingled and the environment is destroyed after each execution.

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