How to Use the Codefresh MCP in Pydantic AI

Q: How does the deprecated HTTP client compare to the new toolset?

You should avoid MCPServerHTTP and use the unified MCPToolset approach. This ensures smooth, type-safe streaming when fetching build data via getbuildexecutiondetails.

Get compile-time safety for your Codefresh deployments using Pydantic AI to validate every MCP action.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codefresh MCP to Pydantic AI

Create your Vinkius account to connect Codefresh 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 Codefresh with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe GitOps with the Codefresh MCP Server

Stop guessing if your agent parsed the build status correctly. This integration uses `get_build_execution_details` and validates the returned payload against strict Pydantic models at runtime. If the API schema changes or returns unexpected nulls, your agent throws an immediate validation error instead of silently corrupting your deployment pipeline.

Validate Pipeline Configurations in Pydantic AI

Ensure your deployment parameters are correct before running them with this MCP tool. The agent pulls the configuration using `get_pipeline_configuration` and checks it against your internal schema requirements. This prevents malformed YAML from ever reaching your clusters. If a parameter fails validation, the execution stops before `trigger_codefresh_build` is ever called.

Secure Environment and Cluster Discovery

Manage your Kubernetes environments with complete type safety. Your agent calls `list_delivery_clusters` and `list_shared_contexts` to map out active targets and their associated credentials. Every cluster object and secret metadata structure is cast into typed Python objects, making it easy to write clean, bug-free deployment logic.

Setup guide

Set up Codefresh 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": {
        "codefresh-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Codefresh 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 Codefresh. 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 Codefresh 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 Codefresh MCP in Pydantic AI

You use the MCPToolset class pointing to the Vinkius HTTP endpoint and pass it to your agent's `toolsets` argument. This automatically registers actions like `list_codefresh_pipelines`.

Yes, the framework validates all tool arguments before calling `trigger_codefresh_build`. If your agent attempts to pass an invalid pipeline ID, the call is blocked locally.

Yes, Pydantic AI is model-agnostic. You can run a local model to query `list_codefresh_builds` while maintaining strict type validation on the outputs.

You should avoid `MCPServerHTTP` and use the unified `MCPToolset` approach. This ensures smooth, type-safe streaming when fetching build data via `get_build_execution_details`.

Your authentication tokens and shared environments queried through `list_shared_contexts` are parsed directly into transient Pydantic models. They are never logged or persisted, keeping your secrets isolated within the memory space of your running application.

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