How to Use the Gitea MCP in Vercel AI SDK

Q: How do I connect this Gitea MCP server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius HTTP endpoint. Then, pass the tools directly into streamText to let your agent inspect repositories.

Q: How does Vercel AI SDK handle long-running Gitea tool calls?

If a call to listorgrepos takes longer due to a massive organization, the SDK maintains the open connection. The agent processes the repository list sequentially and streams the UI components as soon as the payload arrives.

Q: Do I need separate auth for every user?

You can configure the authProvider in the SDK to pass individual Gitea tokens. This ensures the agent only calls getme and accesses repositories the active user actually owns.

Stream live Gitea repository data and issue updates directly to your React frontends using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Gitea to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Gitea repo discovery in your React frontend

The `list_repos` tool retrieves active repository metadata including clone URLs, stars, and default branches directly to your client. This lets your agent display an interactive list of self-hosted repositories to your users without waiting for a full page reload. By pairing this with the Vercel AI SDK, the returned JSON structure flows directly into your UI components. You can build custom dashboards that render repository cards the millisecond the background API call finishes.

Real-time Gitea issue monitoring via Vercel AI SDK

The `list_issues` tool pulls every active ticket from your self-hosted Gitea instance to keep your team aligned. Your agent calls this tool to gather open items and immediately feeds the raw text into the streaming response window. This setup avoids the typical loading spinners that kill user engagement in web apps. Instead, developers watch their issue boards update line-by-line as the LLM processes the ticket list.

Build interactive PR dashboards with this MCP Server

The `list_pulls` tool exposes active pull requests, allowing your agent to inspect code review states in real-time. This lets your user-facing dashboard show exactly which branches need attention without manual polling. Because this MCP server runs inside a zero-trust sandbox, your user's auth token stays isolated while the SDK streams the pull request details. You get clean UI updates without exposing raw admin credentials to the frontend.

Setup guide

Set up Gitea MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Gitea tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Gitea transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius HTTP endpoint. Then, pass the tools directly into `streamText` to let your agent inspect repositories.

Yes, the MCP client runs perfectly in Edge environments. Your agent uses `list_repos` to query your self-hosted instance without cold-start delays.

If a call to `list_org_repos` takes longer due to a massive organization, the SDK maintains the open connection. The agent processes the repository list sequentially and streams the UI components as soon as the payload arrives.

You can configure the `authProvider` in the SDK to pass individual Gitea tokens. This ensures the agent only calls `get_me` and accesses repositories the active user actually owns.

Your Gitea repository metadata, issue descriptions, and pull request details never persist on Vinkius servers. The MCP connection runs in an isolated, ephemeral sandbox that only handles live transit of the data to your Vercel AI SDK client.

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