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

Get type-safe CI pipelines for Pydantic AI. Use Dagger (Programmable CI) with runtime model validation.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation in Pydantic AI

Every response from `execute_graphql_query` is checked against your Pydantic schemas. If the engine returns unexpected data, the agent crashes before the error propagates. This prevents silent failures during your build process. You define the shape of the data, and the agent enforces that contract during every single pipeline step.

Host environment queries for Pydantic AI

Use `query_host` to inspect the underlying machine state. Your agent makes decisions based on real hardware or OS specs, ensuring build compatibility. This provides the agent with environmental context. It knows if it's running in a Linux container or a local environment before it triggers a complex build command.

Manage cache volumes in Pydantic AI

Create and track cache volumes using `query_cache_volume`. Your agent manages the persistence of build layers, speeding up repeated execution tasks significantly. This keeps your pipelines fast. The agent intelligently reuses existing volumes, only rebuilding the parts of the graph that have actually changed.

Setup guide

Set up Dagger (Programmable CI) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

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

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Dagger (Programmable CI) tools.",
)

result = await agent.run("List recent Dagger (Programmable CI) transactions")
print(result.output)

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 Pydantic AI

The Pydantic AI framework validates the tool output automatically. You just define your models, and the toolset handles the conversion and validation at runtime.

Yes, the toolset is fully async. It integrates into your existing agent loops without blocking, allowing for concurrent build operations if your logic requires it.

The server supports Server-Sent Events for real-time updates. You configure the transport in your toolset, and the agent stays updated as the build progresses.

Your agent can check the version before starting a build. If the schema changes, your Pydantic models will catch the discrepancy immediately, preventing runtime errors.

Your build configuration remains local to the engine. The server uses strict schema-based memory protection to ensure no data leaks occur between your agent's validation steps.

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