How to Use the Dagger (Programmable CI) MCP in Cursor

Q: How does Cursor use Dagger (Programmable CI) to debug broken build steps?

When a build fails, Cursor calls executegraphqlquery to inspect the pipeline state. The agent then analyzes the container logs and edits your code to fix the issue on the spot.

Q: Can I manage build secrets inside Cursor using the Dagger (Programmable CI) MCP Server?

Yes, you can. Cursor invokes querysecret to mount local environment variables or files into your container runs. This lets you run authenticated tests without hardcoding keys in your workspace.

Q: How does the Dagger (Programmable CI) extension help Cursor write pipeline modules?

The editor calls querycurrentmodule to read your current module's structure and schema. Cursor then suggests precise TypeScript or Go code to expand your pipeline steps.

Q: What happens when I request a file from a URL?

The agent triggers queryhttp to download files directly into your pipeline workspace. This MCP tool lets you fetch external binaries or test assets during a run.

Write code and run Dagger (Programmable CI) pipelines side-by-side in Cursor, generating working code with live container data.

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 Cursor

Create your Vinkius account to connect Dagger (Programmable CI) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inline Container Debugging

This Dagger (Programmable CI) MCP Server lets Cursor spin up scratch containers for inline debugging. Your editor uses `query_container` to create these environments and test your code changes against real systems instantly. Cursor reads the resulting container state to write code that matches your actual environment. It pulls files via `query_http` to verify external dependencies are correct before committing changes to your workspace.

Automated Module Queries via MCP Server

Querying active pipeline modules is automated through this Dagger (Programmable CI) toolset. Cursor calls `query_current_module` to inspect your active configuration and suggest accurate updates. The editor reads the local schema, then writes raw queries. It runs `execute_graphql_query` to validate your custom pipeline code before you run it in production.

Host Environment Sync

Syncing your host environment with your active editor is managed by this Dagger integration. Cursor calls `query_host` to check your local system paths, ensuring your pipeline configurations match your actual machine setup. To keep builds fast, the editor uses `query_cache_volume` to map local directories to your container runs. You get instant feedback without waiting for full rebuilds.

Setup guide

Set up Dagger (Programmable CI) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Dagger (Programmable CI) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Dagger (Programmable CI) transactions." If the MCP tools are loaded correctly, Cursor will call the Dagger (Programmable CI) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "dagger-programmable-ci-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

When a build fails, Cursor calls `execute_graphql_query` to inspect the pipeline state. The agent then analyzes the container logs and edits your code to fix the issue on the spot.

Yes, you can. Cursor invokes `query_secret` to mount local environment variables or files into your container runs. This lets you run authenticated tests without hardcoding keys in your workspace.

The editor calls `query_current_module` to read your current module's structure and schema. Cursor then suggests precise TypeScript or Go code to expand your pipeline steps.

The agent triggers `query_http` to download files directly into your pipeline workspace. This MCP tool lets you fetch external binaries or test assets during a run.

Your git repository details and container IDs are kept strictly within your local Cursor environment. The server communicates via local JSON-RPC, ensuring no pipeline configurations or build metadata leak to third-party servers.

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