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

Q: How does Windsurf use Dagger (Programmable CI) to speed up local builds?

Cascade uses the querycachevolume tool to persist build caches between test runs. Instead of rebuilding your entire project on every save, the agent mounts the cache volume automatically, cutting down compilation times significantly.

Q: Can Windsurf run complex pipelines via Dagger (Programmable CI) without human intervention?

Yes, Cascade chains tools like executegraphqlquery and querycontainer to construct multi-stage build DAGs autonomously. It monitors the output, fixes errors in your code if the build fails, and runs it again.

Q: How do I configure Dagger (Programmable CI) inside Windsurf?

You can add the MCP Server under the mcpServers block in your /.codeium/windsurf/mcpconfig.json file. Once saved, Cascade instantly discovers the GraphQL and container tools and starts using them to run your pipelines.

Run your local build pipelines and spin up containers autonomously inside Windsurf using Cascade.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-stage Dagger builds directly inside Windsurf.

This MCP Server exposes the `execute_graphql_query` tool so Cascade can assemble and run entire pipeline DAGs without waiting for your manual approval. The tool lets your editor talk directly to the Dagger Engine, translating your high-level build goals into raw GraphQL execution. Cascade reads your workspace files, plans the compilation steps, and fires off `query_container` to isolate the build. It doesn't just suggest commands; it spins up the scratch environment, verifies the container ID, and reports back.

Manage state and dependencies on the fly.

The `query_cache_volume` tool lets Windsurf handle heavy package caches so your test runs don't start from scratch every time. This MCP integration detects your node_modules or cargo registry and mounts the cache volume before running the next step in the sequence. If a build fails due to a missing dependency, Cascade hooks into `query_directory` to initialize a clean workspace, fixes the config file, and re-runs the pipeline. You get fast feedback loops because the editor manages the state programmatically.

Pull remote assets and secrets securely.

Use the MCP connection to trigger `query_http` to pull external binaries or test assets straight into your active container environment. Cascade combines this with `query_git` to fetch specific branches or commits, ensuring your testing pipeline runs against the exact code state you are editing. When your build needs access tokens, Cascade calls `query_secret` to mount environmental variables or file paths without exposing plain-text keys in your editor's history. It keeps your pipeline secure while maintaining fully autonomous execution.

Setup guide

Set up Dagger (Programmable CI) MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Dagger (Programmable CI) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Dagger (Programmable CI) payment history." If connected, Cascade will call the Dagger (Programmable CI) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses the `query_cache_volume` tool to persist build caches between test runs. Instead of rebuilding your entire project on every save, the agent mounts the cache volume automatically, cutting down compilation times significantly.

Yes, Cascade chains tools like `execute_graphql_query` and `query_container` to construct multi-stage build DAGs autonomously. It monitors the output, fixes errors in your code if the build fails, and runs it again.

You can add the MCP Server under the `mcpServers` block in your `~/.codeium/windsurf/mcp_config.json` file. Once saved, Cascade instantly discovers the GraphQL and container tools and starts using them to run your pipelines.

Cascade catches the error returned by the engine, reads the GraphQL failure logs, and corrects the query or your code. It will attempt to fix the root cause, like creating a missing directory with `query_directory`, and retry.

This server handles sensitive GraphQL queries, container IDs, and repository credentials. By using `query_secret`, Windsurf passes env-based or file-based keys directly to the local Dagger daemon, meaning your actual API tokens and passwords never get sent to external AI servers or logged in plain text.

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