How to Use the Gitea MCP in Google ADK

Q: Can Gemini reason over large Gitea pull request lists using Google ADK?

Yes. The listpulls tool returns structured metadata that Gemini processes easily within its large context window. This allows the Google ADK to summarize hundreds of open pull requests in a single reasoning step.

Feed self-hosted Gitea repository data directly into Gemini long-context pipelines 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 Gitea MCP to Google ADK

Create your Vinkius account to connect Gitea 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 Gitea with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Entire Codebases with Gemini

The `get_repo` tool retrieves complete metadata for a target Gitea repository, which the Google ADK ingest pipeline feeds directly into Gemini's million-token context window. This allows your Google ADK agent to compare live Gitea repository states against historical data warehouses in BigQuery. You get factual, data-backed code audits without manually copying files. By combining this with `list_branches`, the Google ADK agent maps out active development paths across your self-hosted environment. The Google ADK uses this structural map to identify orphaned features that haven't seen a commit in months.

Mine Gitea Issues for Vertex AI Training

The `list_issues` tool pulls issue logs from Gitea, providing raw text for training custom support models on Vertex AI. The Google ADK coordinates these calls to build clean datasets from your self-hosted developer conversations. The agent filters issues by status, labels, and creators before exporting them to Google Cloud Storage. When a specific bug needs deep investigation, the Google ADK agent calls `get_issue` to extract the full conversation thread. This prevents your Gemini model from hallucinating context during automated bug triage.

Map Organizations to BigQuery via MCP Server

The `get_org` tool fetches administrative details for a specific Gitea organization, enabling enterprise-wide compliance reporting. Your Google ADK agent executes this tool alongside `list_org_repos` to audit project ownership across departments. The resulting map is written directly to BigQuery to track resource allocation. Using this Gitea MCP Server, your Gemini models can cross-reference Gitea user profiles via `get_me` with corporate directories. This keeps your self-hosted Git server aligned with enterprise access control policies.

Setup guide

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

You initialize McpToolset using the streamable HTTP parameters pointing to Vinkius. The Google ADK exposes tools like list_repos and list_pulls directly to your Gemini-powered agent.

Yes. The list_pulls tool returns structured metadata that Gemini processes easily within its large context window. This allows the Google ADK to summarize hundreds of open pull requests in a single reasoning step.

Yes. The Google ADK passes your authenticated Vinkius token via the MCP Server transport layer. This ensures the agent only accesses Gitea endpoints like get_me or list_orgs that your token permits.

The Google ADK catches the transport error from the MCP Server and presents it as a tool failure to the model. Gemini then decides whether to retry the call or report the issue back to your application.

No. Your pull requests, organization lists, and user profiles are processed through secure, private endpoints. The Vinkius infrastructure uses isolated execution environments, and Google Cloud ensures your data is not used to train public models.

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