How to Use the Forgejo (Gitea Fork) MCP in Google ADK

Q: How do I configure Forgejo (Gitea Fork) with Google ADK?

Install google-adk and set up an McpToolset using StreamableHttpServerParameters pointing to your MCP URL. Pass that toolset into your LlmAgent initialization.

Q: Can I restrict Forgejo (Gitea Fork) tools in Google ADK?

Yes. Use the toolnames parameter when defining your toolset. This prevents the agent from calling tools like createtoken if it only needs version data.

Q: Does the agent wait for the Forgejo workflow to finish?

The dispatchworkflow tool triggers the action and returns a success response for the trigger itself. The agent must poll the API separately if you want it to wait for the final build status.

Connect your Gemini agents to self-hosted repositories using the Google ADK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forgejo (Gitea Fork) MCP to Google ADK

Create your Vinkius account to connect Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

End-to-End Workflow Execution

The `dispatch_workflow` tool allows your Gemini agent to trigger Forgejo Actions manually. Enterprise agents need to close the loop between code analysis and deployment. You point the agent at a repository, and it pushes the button to run the pipeline. Google ADK feeds the execution results straight back into Gemini's massive context window. If the pipeline fails, the agent reads the logs, fixes the issue, and triggers the workflow again. It handles the entire cycle without paging a human.

On-Demand Access Tokens

This MCP Server provides `create_token` so your agent can provision personal access tokens programmatically. Static, long-lived credentials are a security nightmare. Your agent requests a fresh token for a specific task and discards it when finished. You restrict which tools the agent sees using the `tool_names` filter in the Google ADK. If a specific LlmAgent doesn't need token creation rights, you just exclude it from the `McpToolset`. Security policies stay intact.

Google ADK Version Validation

The `get_forgejo_version` and `get_gitea_version` tools return the exact version strings of your target instance. Self-hosted environments rarely run the latest release. The agent pulls this metadata to understand what API features are actually supported. You don't want your agent guessing how the API behaves. By checking the Gitea-compatible version first, Gemini uses its long-context reasoning to adapt its subsequent API calls. It avoids hitting deprecated endpoints entirely.

Setup guide

Set up Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) 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="Forgejo (Gitea Fork)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Forgejo (Gitea Fork) 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 Forgejo. 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 Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) MCP in Google ADK

Install `google-adk` and set up an `McpToolset` using `StreamableHttpServerParameters` pointing to your MCP URL. Pass that toolset into your `LlmAgent` initialization.

Yes. Use the `tool_names` parameter when defining your toolset. This prevents the agent from calling tools like `create_token` if it only needs version data.

The `dispatch_workflow` tool triggers the action and returns a success response for the trigger itself. The agent must poll the API separately if you want it to wait for the final build status.

The Google ADK supports both Stdio and HTTP transports. You can run the server locally as a subprocess or host it remotely via HTTP.

This integration touches API tokens, workflow trigger payloads, and version metadata. Google ADK routes these details directly into your Gemini context window. Google Cloud's enterprise data agreements ensure your private repository metadata is never 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