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

Q: How do I connect the Forgejo (Gitea Fork) MCP server to Vercel AI SDK?

Call createMCPClient with your transport configuration. Pass the resulting mcpClient.tools() into streamText so your agent can trigger Forgejo workflows. Always call mcpClient.close() when the session ends.

Q: How do I handle token creation securely in Vercel AI SDK with Forgejo (Gitea Fork)?

Use the authProvider configuration to manage user sessions. When the agent calls createtoken, it relies on the authenticated context to ensure it only generates credentials the current user is permitted to hold.

Stream Forgejo Actions workflow triggers and version checks directly into your React frontend using 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 Forgejo (Gitea Fork) MCP to Vercel AI SDK

Create your Vinkius account to connect Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CI/CD Status with Vercel AI SDK

Your users don't want to stare at a spinner while a deployment kicks off. By wiring this MCP Server into your Vercel AI SDK setup, you stream live workflow execution data straight to the browser. The agent calls `dispatch_workflow` and the UI updates immediately with the job status. This works perfectly in edge functions. You pass the tools into `streamText`, and the end user watches the agent negotiate the Forgejo API in real-time, confirming the build pipeline started without needing a page refresh.

Live Token Generation

Building an internal developer portal requires handling credentials. Instead of writing custom backend logic to talk to Forgejo, your AI client handles it. It calls `create_token` based on the user's prompt and pushes the new personal access token directly into the chat component. Because Vercel AI SDK supports the `authProvider` block, you keep the token generation secure. The agent gets just enough context to issue the credential, and the user gets their key instantly.

Instant API Compatibility Checks

Self-hosted environments drift. A user might run an older Gitea instance or a bleeding-edge Forgejo build. Your agent needs to know what it is talking to before firing off commands. It runs `get_forgejo_version` or `get_gitea_version` and streams the metadata back to the client. If the API doesn't match your app's requirements, the agent halts and tells the user exactly why the workflow cannot proceed.

Setup guide

Set up Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) 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 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 Vercel AI SDK

Call `createMCPClient` with your transport configuration. Pass the resulting `mcpClient.tools()` into `streamText` so your agent can trigger Forgejo workflows. Always call `mcpClient.close()` when the session ends.

Yes. When the agent triggers a Forgejo Action, the tool execution result streams directly to your React or Next.js frontend. The user sees the pipeline start instantly.

It does. The HTTP transport layer works perfectly on the Edge. You can run `get_gitea_version` checks globally without spinning up a heavy Node container.

Use the `authProvider` configuration to manage user sessions. When the agent calls `create_token`, it relies on the authenticated context to ensure it only generates credentials the current user is permitted to hold.

The agent accesses server versions, repository workflow names, and generated personal access tokens. Vercel AI SDK transmits these strings directly to your configured model provider. You must secure your prompt to prevent the agent from leaking the raw output of `create_token` if it isn't meant for the end user.

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