How to Use the GitHub MCP in Google ADK

Q: How do I configure GitHub credentials in my google-adk setup?

Pass your Vinkius endpoint URL to the McpToolset class inside your Google ADK code. This handles the connection securely, letting your Gemini models access tools like getmygithubprofile without exposing raw credentials.

Q: Can I filter which GitHub tools are exposed to google-adk?

Yes, you can use the toolnames parameter in your Google ADK toolset configuration to expose only specific tools. For instance, you can limit the agent to searchgithubcode and block any write actions.

Q: How does google-adk handle large code search results from GitHub?

When your agent calls searchgithubcode, the Gemini model uses its long-context window to parse the search results. Google ADK feeds this output directly into the prompt context, allowing the model to find relevant snippets without hitting token limits.

Connect your Google ADK enterprise agents to the GitHub MCP Server to analyze codebases and manage issues at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect GitHub MCP to Google ADK

Create your Vinkius account to connect GitHub to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup GitHub with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Analyze large codebases using Gemini long context

The `get_file_contents` tool feeds raw code files directly into your Google ADK agent. Because Gemini models handle over a million tokens of context, your agent can read entire directory structures in one go without losing track of your system architecture. You can combine this massive context window with BigQuery data to run advanced analysis on your development velocity. Your agent can pull repository structures and cross-reference them with your internal cloud databases in seconds.

Query repository metadata across Google Cloud

The `get_repository_details` tool retrieves metadata that your Google ADK agents can use to organize your cloud deployment pipelines. This lets your Vertex AI models match active code repositories with their corresponding cloud infrastructure. By calling `list_user_repositories` and `list_repository_forks`, your agent gets a complete picture of your source control setup. It can then automatically trigger Google Cloud Build runs based on the active branches it discovers.

Automate issue tracking via the Google ADK MCP Server

The `create_new_issue` tool allows your Google ADK agent to write new tracking tickets directly from your cloud application logs. When a Vertex AI model detects a system error, it can immediately open a structured issue in the correct repository. The agent can also run `list_repo_issues` to check if a ticket for that specific bug already exists. This prevents your team from getting flooded with duplicate bug reports while maintaining an accurate log of system health.

Setup guide

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

Pass your Vinkius endpoint URL to the `McpToolset` class inside your Google ADK code. This handles the connection securely, letting your Gemini models access tools like `get_my_github_profile` without exposing raw credentials.

Yes, you can use the `tool_names` parameter in your Google ADK toolset configuration to expose only specific tools. For instance, you can limit the agent to `search_github_code` and block any write actions.

When your agent calls `search_github_code`, the Gemini model uses its long-context window to parse the search results. Google ADK feeds this output directly into the prompt context, allowing the model to find relevant snippets without hitting token limits.

Yes, this MCP Server works with both transport protocols. You can run it as a hosted service via HTTP or run it locally using Stdio within your Google Cloud development environment.

Your GitHub repository details and code contents are processed in memory. The Vinkius MCP infrastructure uses secure V8 isolates, meaning no source code or API tokens are ever cached, ensuring your intellectual property remains private and isolated.

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