How to Use the Dagger (Programmable CI) MCP in Mastra AI

Q: How do I add Dagger (Programmable CI) to Mastra AI workflows?

Install @mastra/mcp@latest via your package manager. Initialize a new MCPClient and pass the Vinkius URL into the servers object. Call listTools() and spread the results into your agent's tool array.

Q: Does Dagger (Programmable CI) require human approval in Mastra AI?

You decide which operations need a manual check. Setting requireToolApproval on destructive actions pauses the workflow. A developer reviews the pipeline changes before the agent proceeds.

Build resilient Dagger CI workflows with Mastra AI. Handle container failures and retry build steps automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dagger (Programmable CI) MCP to Mastra AI

Create your Vinkius account to connect Dagger (Programmable CI) 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 Dagger (Programmable CI) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional CI branching via MCP Server

`execute_graphql_query` lets your workflow engine construct complex Dagger graphs on the fly. If a build step fails, Mastra catches the error and branches the logic. The agent can automatically retry the query with different parameters or fall back to a previous known-good state. `query_container` spins up scratch environments for testing. Container allocation becomes fully programmatic. When those tests crash, the framework's exponential backoff kicks in, requesting a fresh container ID until the suite passes or hits the max attempt limit.

Persistent caching across workflow runs

Calling `query_cache_volume` constructs a persistent layer for your dependencies. Rebuilding from zero wastes compute time and delays deployments. Your agent attaches this volume to subsequent tasks, cutting execution time down to seconds. `query_directory` generates empty folders and returns their IDs for the workflow to populate. Directory structures need mapping before execution. Mastra sequences these operations perfectly, ensuring the filesystem exists before the compiler tries to write to it.

External resource resolution

`query_git` fetches repository data right when the workflow needs it. Pulling specific code versions requires exact timing in the pipeline. If the Git provider rate-limits the request, the built-in retry mechanism waits and tries again automatically. `query_http` grabs files from URLs. Downloading binaries from third parties breaks builds constantly. The workflow engine verifies the download, and if it gets a 502 Bad Gateway, it pauses and retries instead of failing the entire deployment.

Setup guide

Set up Dagger (Programmable CI) 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 Dagger (Programmable CI) 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: "dagger-programmable-ci-mcp-client",
  servers: {
    "dagger-programmable-ci-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Dagger (Programmable CI) 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 Dagger. 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 Dagger (Programmable 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 Dagger (Programmable CI) MCP in Mastra AI

Install `@mastra/mcp@latest` via your package manager. Initialize a new `MCPClient` and pass the Vinkius URL into the servers object. Call `listTools()` and spread the results into your agent's tool array.

That exact scenario is what the framework handles best. You configure exponential backoff on the agent level. If a container crashes, the system waits and triggers the MCP tool again automatically.

You decide which operations need a manual check. Setting `requireToolApproval` on destructive actions pauses the workflow. A developer reviews the pipeline changes before the agent proceeds.

The client auto-detects the right connection method for the Vinkius endpoint. It switches between Streamable HTTP or SSE without any manual configuration. You just provide the URL and let the engine route the traffic.

Everything executes inside an ephemeral V8 Isolate Sandbox. The Vinkius MCP server reads your deployment secrets and API keys to configure the containers. Zero-trust architecture ensures those credentials vanish the moment the workflow finishes.

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