How to Use the GitHub MCP in Google ADK

Q: How do I initialize the GitHub MCP Server in Google ADK?

You pass the Vinkius server URL to the StreamableHttpServerParameters constructor. Then, register it as an McpToolset inside your LlmAgent setup to expose tools like getmyprofile directly to Gemini.

Q: Can I limit which GitHub tools Google ADK can access?

Yes, you can use the optional toolnames filter during initialization to restrict tool access. For example, you can expose listrecentnotifications while blocking write tools like createnewissue to enforce strict security boundaries.

Q: How does Google ADK handle large file payloads from GitHub?

The getfilecontent tool returns raw file data directly to the ADK toolset. Gemini's million-token context window easily digests these large payloads without truncation, and Vinkius ensures the transfer is secure.

Give Google ADK agents direct access to GitHub resources for long-context Gemini reasoning and enterprise workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitHub MCP to Google ADK

Create your Vinkius account to connect GitHub 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 GitHub with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context repository analysis using Google ADK

The `get_file_content` tool feeds entire codebases into your Gemini model's massive context window. It pulls raw source files so your agent can reason over thousands of lines of code at once. To find the right files, the agent uses `list_my_repositories` via the MCP connection to locate the correct repository. It then uses `list_repo_branches` to target the active branch, getting the exact file versions it needs.

Automated issue and pull request tracking

The `list_repository_issues` tool retrieves open issues so your enterprise agent can cross-reference them with BigQuery performance metrics. It identifies which bugs are causing production alerts and prioritizes them. When the agent resolves an issue, it uses `list_pull_requests` to find the corresponding pull request. It checks the merge status and keeps your team updated without manual status checks.

Organization-wide project search

The `search_repositories` tool scans all public and private repositories across your enterprise organizations. It helps your agent discover active codebases, find specific configuration files, and track down shared libraries. This MCP Server allows your agent to query `list_my_organizations` to map out the entire corporate structure first. It then queries each organization to build a complete index of internal projects.

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

You pass the Vinkius server URL to the `StreamableHttpServerParameters` constructor. Then, register it as an `McpToolset` inside your `LlmAgent` setup to expose tools like `get_my_profile` directly to Gemini.

Yes, you can use the optional tool_names filter during initialization to restrict tool access. For example, you can expose `list_recent_notifications` while blocking write tools like `create_new_issue` to enforce strict security boundaries.

The `get_file_content` tool returns raw file data directly to the ADK toolset. Gemini's million-token context window easily digests these large payloads without truncation, and Vinkius ensures the transfer is secure.

Yes, this MCP integration runs on Vinkius's managed infrastructure and connects to any ADK agent running on Vertex AI or Cloud Run. Your agent can query `list_my_gists` and combine that data with BigQuery tables.

The server handles repository files, issue text, and commit histories. Vinkius runs every tool execution in an ephemeral V8 sandbox that is destroyed instantly after the tool returns its data, meaning no code is cached or stored on the platform.

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