How to Use the Forgejo (Gitea Fork) MCP in Mastra AI

Q: How do I load the Forgejo (Gitea Fork) MCP tools into Mastra AI?

Initialize MCPClient with your server URL, then call mcpClient.listTools(). Spread those tools directly into your Mastra Agent configuration. The framework auto-detects SSE or Streamable HTTP transports.

Q: Should I use human-in-the-loop for Forgejo (Gitea Fork) token creation in Mastra AI?

You should. Enable requireToolApproval for the createtoken tool. This forces a human to click approve before the agent generates a live personal access token on your git server.

Q: How does Mastra branch logic based on Forgejo version checks?

The agent calls getforgejoversion and evaluates the response. You configure Mastra to run one sequence if the version supports a specific Forgejo Action, and a fallback sequence if it detects an older Gitea instance.

Build resilient CI/CD workflows and automated Forgejo token rotation pipelines using Mastra AI 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 Mastra AI

Create your Vinkius account to connect Forgejo (Gitea Fork) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient Workflow Triggers

Network calls to self-hosted git instances fail. That is just reality. When you use Mastra AI to call `dispatch_workflow`, you get automatic retries with exponential backoff built right into the agent's logic. If the Forgejo server drops the connection, the agent waits and tries again before throwing an error. You build a deployment pipeline that actually survives a brief network blip or a runner queue timeout.

Conditional Token Rotation via MCP Server

Managing personal access tokens across a fleet of developers is tedious. You can build a Mastra workflow that checks token expiration dates, then conditionally calls `create_token` only when a replacement is necessary. If the token generation fails due to permissions, Mastra branches the workflow. It skips the Forgejo update and immediately notifies an admin via a different tool, keeping the pipeline moving instead of crashing.

Pre-Flight Version Validation

You don't want to trigger a workflow if the target server runs an incompatible API. Your agent runs `get_forgejo_version` and `get_gitea_version` as step one of the deployment sequence. Mastra evaluates that metadata. If the version matches your requirements, the workflow proceeds to trigger the Forgejo Action. If it fails, the agent halts the run gracefully and logs the exact version mismatch.

Setup guide

Set up Forgejo (Gitea Fork) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Forgejo (Gitea Fork) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "forgejo-gitea-fork-mcp-client",
  servers: {
    "forgejo-gitea-fork-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Forgejo (Gitea Fork) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Forgejo (Gitea Fork) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Forgejo (Gitea Fork) transactions"
);
console.log(result.text);

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 Mastra AI

Initialize `MCPClient` with your server URL, then call `mcpClient.listTools()`. Spread those tools directly into your Mastra Agent configuration. The framework auto-detects SSE or Streamable HTTP transports.

Yes. Mastra handles retries automatically. If the Forgejo API rate limits your request to trigger a pipeline, the agent backs off and tries again based on your workflow rules.

You should. Enable `requireToolApproval` for the `create_token` tool. This forces a human to click approve before the agent generates a live personal access token on your git server.

The agent calls `get_forgejo_version` and evaluates the response. You configure Mastra to run one sequence if the version supports a specific Forgejo Action, and a fallback sequence if it detects an older Gitea instance.

This integration processes repository names, workflow triggers, and live API tokens. Mastra retains this data in its workflow state to handle retries and branching. Keep your state storage secure, especially if the agent generates administrative tokens via `create_token`.

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