How to Use the Prismic MCP in Pydantic AI

Q: Does Pydantic AI work with Prismic document lists?

Yes. When you use listdocumentsbytype, the tool returns a list that you can validate against a list model in Pydantic. It handles complex nested objects easily.

Enforce strict schema validation on your Prismic content using Pydantic AI for reliable agent responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Prismic MCP to Pydantic AI

Create your Vinkius account to connect Prismic to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Prismic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe Prismic document retrieval in Pydantic AI

Fetch documents with `get_document_by_id` and have the results validated against your Pydantic models. If the content structure is wrong, the agent stops immediately. This prevents silent data corruption. You get a clear validation error the moment the CMS returns a field that doesn't match your expected types.

Validating Prismic queries within Pydantic AI

Use `get_query_form_schema` to understand the query requirements before running a search. Your agent validates its query parameters against this schema. This reduces runtime errors and ensures your search predicates are always valid. It keeps your agent running smoothly against your custom types.

Listing Prismic types for Pydantic AI models

Map your CMS structure to Python classes using `list_custom_types`. Your agent uses these definitions to build its internal data models. This keeps your application code in sync with your CMS. If you change a type in Prismic, your Pydantic model throws a validation error, alerting you to update your code.

Setup guide

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

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

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

Pydantic AI ensures that every piece of content coming from Prismic strictly adheres to your defined Python models. It kills the risk of hallucinated fields.

Yes. When you use `list_documents_by_type`, the tool returns a list that you can validate against a list model in Pydantic. It handles complex nested objects easily.

Install the mcp extra, instantiate the MCPToolset with your server endpoint, and pass it to the agent. It is a unified approach that handles all transport protocols.

The Pydantic validator will fail immediately. This gives you a stack trace pointing exactly to the field that violated your schema, preventing the agent from proceeding.

They stay off your local machine. Vinkius manages the auth token, and the agent only uses the server to perform allowed actions on your CMS data.

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