How to Use the Cosmic MCP in Pydantic AI

Q: How do I connect my Pydantic AI agent to Cosmic?

Install the library using pip install "pydantic-ai-slimmcp". Then, initialize MCPToolset with your Vinkius HTTP URL to load the MCP Server tools.

Build type-safe content agents with Pydantic AI to validate every Cosmic CMS draft and schema change at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cosmic MCP to Pydantic AI

Create your Vinkius account to connect Cosmic 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 Cosmic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict JSON payload validation with Pydantic AI

Handing content creation to an LLM is risky if it hallucinates fields. Pydantic AI stops mistakes by validating the output of `create_cms_object` against your strict Python models before the draft ever hits Cosmic. If your agent tries to patch a Cosmic object using `patch_cms_object` with incorrect types, the runtime catches the error immediately. Catching these issues early keeps your headless CMS database pristine and prevents broken JSON from corrupting your frontend.

Type-safe schema discovery via Cosmic MCP Server

Dynamic content structures require strict validation. This Cosmic MCP Server allows Pydantic AI to run `list_schema_types` to discover what content models exist in your bucket. The agent then extracts the exact property structures with `get_schema_details`. Because Pydantic AI enforces type safety, it maps these Cosmic properties to runtime schemas, ensuring your Python code knows exactly what fields to expect.

Safe media asset tracking and deletion

Managing media assets with code requires reliable metadata. Pydantic AI uses `list_uploaded_media` to fetch your Cosmic files, parsing the returned arrays into strongly-typed objects that your application can safely navigate. When retrieving a specific file with `get_media_asset`, the framework validates the asset's ID and dimensions. If you need to run cleanup scripts in Pydantic AI, the agent can call `wipe_media_asset` knowing there is zero risk of passing a malformed identifier to Cosmic.

Setup guide

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

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

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

Install the library using pip install "pydantic-ai-slim[mcp]". Then, initialize MCPToolset with your Vinkius HTTP URL to load the MCP Server tools.

The framework will immediately raise a validation error. Instead of silently passing malformed JSON to your app, Pydantic AI forces the agent to correct its input or fail safely.

Yes, you can. Since Pydantic AI is model-agnostic, you can connect the Cosmic tools to local models or commercial APIs while maintaining strict type validation.

Yes. You can loop through objects, validate their fields against your Pydantic models, and update them using patch_cms_object to ensure complete data consistency across your CMS.

Your media assets and draft payloads are processed entirely within your local Pydantic AI environment. The Vinkius gateway handles authentication via ephemeral sandboxes, meaning your sensitive CMS data is never stored or logged.

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