How to Use the Woodpecker CI MCP in Vercel AI SDK

Q: Can I list all repositories using Woodpecker CI with Vercel AI SDK?

Yeah, sure thing. Just use listrepos. This tool gives your agent the full manifest of every repository hosted on the server so you know exactly what's available.

Q: How does Woodpecker CI handle pipeline restarts with Vercel AI SDK?

It’s straightforward. You just call restartpipeline and your agent handles the rest. The result streams back to your UI, telling you when the new build is running.

Streamline CI/CD actions from your UI with Vercel AI SDK and Woodpecker CI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Woodpecker CI MCP to Vercel AI SDK

Create your Vinkius account to connect Woodpecker CI 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 Woodpecker CI with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control the entire MCP Server lifecycle.

Need to check up on a repo or manage credentials? You can grab details using `get_repo` and look up specific setups with `lookup_repo`. It’s also simple enough to fix broken webhook connections if you run `repair_repo`. Don't forget the user side. Your agent can list all repos via `list_repos`, or even delete an entire project using `delete_repo`. This gives your AI client total visibility into the CI environment.

Manage pipelines and agents in real-time.

Watching a build run is tedious. With Woodpecker CI, you can trigger a manual pipeline with `trigger_pipeline` or start over by calling `restart_pipeline`. If it's running wild, just hit the brakes using `cancel_pipeline`. For agents, your agent handles everything. List them all with `list_agents`, and if something breaks, you can update an existing one using `update_agent`.

Securely manage secrets and credentials.

Credentials are critical. Your AI client can create a secure global secret using `create_global_secret`. You also get granular control over project-level keys by listing them with `list_repo_secrets`. It’s all about keeping things locked down. Besides secrets, you can check who has permission for an organization using `get_org_permissions`. This keeps your entire workflow safe.

Setup guide

Set up Woodpecker CI 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 Woodpecker CI 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 Woodpecker CI 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 Woodpecker CI. 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 Woodpecker CI 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 Woodpecker CI MCP in Vercel AI SDK

You call the MCP client's tools directly from your frontend code. The results stream live, so your user sees the data appear in real-time instead of waiting for a loading spinner.

Yeah, sure thing. Just use `list_repos`. This tool gives your agent the full manifest of every repository hosted on the server so you know exactly what's available.

It’s straightforward. You just call `restart_pipeline` and your agent handles the rest. The result streams back to your UI, telling you when the new build is running.

Absolutely. You can create and list secrets using tools like `create_global_secret` or `list_repo_secrets`. Your agent treats these credentials just like any other data point.

The server primarily touches repository secrets and global secrets. These are the critical pieces of sensitive information your agent needs to manage during deployment cycles.

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